Wireless communication method, terminal and network side device

Abstract

The application discloses a wireless communication method, a terminal and a network side device, and belongs to the communication field. The wireless communication method of the application embodiment comprises the following steps: a terminal reports first information; wherein the first information is used for indicating at least one of the following: prediction accuracy of T1 pieces of interference information, T1 is greater than or equal to 1; prediction accuracy of interference information in T2 time domain units, T2 is greater than or equal to 1; and performance information of an artificial intelligence (AI) model.

Description

Technical Field

[0001] This application belongs to the field of communication technology, specifically relating to a wireless communication method, terminal, and network-side equipment. Background Technology

[0002] The terminal may be subject to interference from various sources, which may lead to poor signal transmission quality and ultimately cause the terminal to receive errors or fail to receive signals.

[0003] The terminal can predict and report interference information. Specifically, the terminal can predict and report interference information based on a deployed artificial intelligence (AI) model or algorithm (hereinafter referred to as AI model), and the network-side equipment can schedule communication resources for the terminal based on the interference information predicted by the terminal.

[0004] However, the predictive performance of AI models is often affected by factors such as the network environment. Therefore, when factors such as the network environment change, the predictive performance of AI models may decline, which in turn leads to the terminal predicting and reporting interference information with low accuracy. When network-side devices schedule communication resources for the terminal based on inaccurate interference information, it will reduce the terminal's communication performance. Summary of the Invention

[0005] This application provides a wireless communication method, a terminal, and a network-side device that can guarantee the communication performance of the terminal.

[0006] In a first aspect, a wireless communication method is provided, executed by a terminal, the method comprising:

[0007] The terminal reports the first piece of information;

[0008] Wherein, the first information is used to indicate at least one of the following:

[0009] The prediction accuracy for T1 interference information is T1≥1;

[0010] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0011] Performance information of artificial intelligence (AI) models.

[0012] Secondly, a wireless communication method is provided, executed by a network-side device, the method comprising:

[0013] The network-side device receives the first information;

[0014] Wherein, the first information is used to indicate at least one of the following:

[0015] The prediction accuracy for T1 interference information is T1≥1;

[0016] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0017] Performance information of artificial intelligence (AI) models.

[0018] Thirdly, a wireless communication device is provided, comprising:

[0019] The sending module is used to report the initial information;

[0020] Wherein, the first information is used to indicate at least one of the following:

[0021] The prediction accuracy for T1 interference information is T1≥1;

[0022] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0023] Performance information of artificial intelligence (AI) models.

[0024] Fourthly, a wireless communication device is provided, comprising:

[0025] The receiving module is used to receive the first information;

[0026] Wherein, the first information is used to indicate at least one of the following:

[0027] The prediction accuracy for T1 interference information is T1≥1;

[0028] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0029] Performance information of artificial intelligence (AI) models.

[0030] Fifthly, a wireless communication device is provided, the device being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the second aspect.

[0031] In a sixth aspect, a terminal is provided, the terminal including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0032] In a seventh aspect, a terminal is provided, including a processor and a communication interface, wherein the communication interface is used to report first information;

[0033] Wherein, the first information is used to indicate at least one of the following:

[0034] The prediction accuracy for T1 interference information is T1≥1;

[0035] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0036] Performance information of artificial intelligence (AI) models.

[0037] Eighthly, a network-side device is provided, the network-side device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the second aspect.

[0038] In a ninth aspect, a network-side device is provided, including a processor and a communication interface, wherein the communication interface is used to receive first information;

[0039] Wherein, the first information is used to indicate at least one of the following:

[0040] The prediction accuracy for T1 interference information is T1≥1;

[0041] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0042] Performance information of artificial intelligence (AI) models.

[0043] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the second aspect.

[0044] Eleventhly, a wireless communication system is provided, comprising: a terminal and a network-side device, wherein the terminal can be used to perform the steps of the method as described in the first aspect, and the network-side device can be used to perform the steps of the method as described in the second aspect.

[0045] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program 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.

[0046] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the wireless communication method as described in the first or second aspect.

[0047] In this embodiment, the terminal reports first information used to determine the accuracy of predictions or the performance information of AI models, enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the communication performance of the terminal. Attached Figure Description

[0048] Figure 1 This is a schematic diagram of a communication system architecture provided in an embodiment of this application.

[0049] Figure 2 This is an example of a neural network structure provided according to an embodiment of this application.

[0050] Figure 3 This is an example of a neuron structure provided according to an embodiment of this application.

[0051] Figure 4 This is an example of an interference prediction module provided according to an embodiment of this application.

[0052] Figure 5 This is a schematic flowchart illustrating a terminal performing interference prediction according to an embodiment of this application.

[0053] Figure 6 This is a schematic flowchart illustrating an interference prediction process performed by a network-side device according to an embodiment of this application.

[0054] Figure 7 This is a schematic flowchart of a wireless communication method provided in an embodiment of this application.

[0055] Figure 8 This is an example of interference information predicted by a terminal, provided in an embodiment of this application.

[0056] Figure 9 This is an example of a method for determining first information provided in an embodiment of this application.

[0057] Figures 10 to 12 This is an example of the first offset value provided in the embodiments of this application.

[0058] Figure 13 This is an example of a thread provided in the embodiments of this application.

[0059] Figure 14 This is a schematic block diagram of a wireless communication device provided in an embodiment of this application.

[0060] Figure 15 This is a schematic block diagram of another wireless communication device provided in the embodiments of this application.

[0061] Figure 16 This is a schematic block diagram of a communication device provided in an embodiment of this application.

[0062] Figure 17 This is a schematic diagram of the hardware structure of a terminal provided in an embodiment of this application.

[0063] Figure 18 This is a schematic block diagram of a network-side device provided in an embodiment of this application. Detailed Implementation

[0064] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0065] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0066] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as the sender explicitly informing the receiver of specific information, the required operation, or the requested result in the instruction sent. An indirect instruction can be understood as the receiver determining the corresponding information based on the instruction sent by the sender, or making a judgment and determining the required operation or requested result based on the judgment result.

[0067] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0068] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can also be referred to as User Equipment (UE), and can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart earphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (APs), or Wireless Fidelity (WiFi) nodes, etc.Among them, base stations can be referred to as Node B (NB), Evolved Node B (eNB), 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, Transmit / Receive Point (TRP), Non-Terrestrial Network (NTN) equipment (such as satellite or high altitude platform stations). The term "base station" can be any suitable term in the field, such as "station" or any other appropriate term in the relevant field, as long as the same technical effect is achieved. The term "base station" is not limited to specific technical terms. It should be noted that the embodiments of this application only use the base station in the NR system as an example for introduction, and do not limit the specific type of base station.

[0069] To facilitate a better understanding of the embodiments of this application, the related technologies are described.

[0070] (I) Artificial Intelligence.

[0071] Artificial intelligence (AI) has been widely applied in various fields. Integrating AI into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but does not limit the specific type of AI module.

[0072] Figure 2 This is an example of a neural network structure provided according to an embodiment of this application.

[0073] like Figure 2 As shown, the structure of a neural network includes an input layer, hidden layers (also called hidden layers), and an output layer. The input of the input layer is X1 to X... nThe output of the output layer is Y. It should be understood that this application uses a neural network as an example for illustration, but does not limit the specific type of AI module.

[0074] Figure 3 This is an example of a neuron structure provided according to an embodiment of this application.

[0075] like Figure 3 As shown, a neural network consists of neurons. The output of a neuron is z, where z = a1w1 + ... + a k w k +…+a K w K Where a1~a K For input, w1~w K σ is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Activation functions include the Sigmoid function, tanh function, Rectified Linear Unit (ReLU) (also known as the linear rectified function), etc.

[0076] The parameters of a neural network are optimized using optimization algorithms. An optimization algorithm is a class of algorithms that minimizes or maximizes an objective function (sometimes called a loss function). 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(.). With the model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. The goal is to find suitable values ​​W and b that minimize the value of the loss function. The smaller the loss value, the closer the AI ​​model is to reality.

[0077] Optimization algorithms are typically based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two stages: forward propagation of the signal and backward propagation of the error. During forward propagation, input samples are introduced from the input layer, processed layer by layer through the hidden layers, and then transmitted to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error among all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is cyclical. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until a pre-set number of learning instances is reached.

[0078] Optimization algorithms can specifically include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, momentum-driven stochastic gradient descent algorithms (such as Nesterov), adaptive gradient descent (Adagrad), gradient descent-based adaptive learning rate optimization algorithm (Adadelta), root mean square prop (RMSprop), and adaptive momentum estimation (Adam), etc.

[0079] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0080] It should be noted that the AI ​​model in this application embodiment may also be referred to as an AI unit, ML (machine learning) model, ML unit, AI structure, AI characteristics, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, an AI model may refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI. An AI model may also be a processing method, algorithm, function, module, or unit for a specific dataset. Furthermore, an AI model may be a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as a Graphics Processing Unit (GPU), Neural Processing Unit (NPU), Tensor Processing Unit (TPU), or Application Specific Integrated Circuit (ASIC). This application does not impose specific limitations in this regard. The specific dataset may include the input and / or output of the AI ​​unit / AI model.

[0081] Optionally, the identifier of the AI ​​unit / AI model may be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific dataset associated with the AI ​​unit / AI model, or an identifier of a specific scenario, environment, channel characteristics, or device related to the AI / ML, or an identifier of a function, characteristic, capability, or module related to the AI / ML. The present invention does not specifically limit this.

[0082] (ii) Interference prediction.

[0083] Knowing predicted future interference information, network-side devices can make better scheduling decisions and coordinate interference between cells to reduce future interference to terminals and improve link quality. For example, network-side devices can avoid scheduling users who are predicted to experience strong interference on future communication resources. Furthermore, based on predicted interference information, network-side devices can more accurately determine the modulation and coding scheme (MCS) to reduce the initial block error rate and transmission latency.

[0084] The terminal side knows the interference information on the communication resources to be scheduled in the future. By utilizing the correlation of interference in the time domain, frequency domain, or spatial domain, it can better eliminate interference during data demodulation and improve decoding accuracy.

[0085] Interference experienced by a terminal may be caused by various sources, such as neighboring base stations, sidelink communication between other UEs, and other UEs. Interference experienced by a UE, also known as Interference Plus Noise (IpN), can change rapidly in the time, frequency, and spatial domains. IpN refers to the sum of the interference power and noise power measured by the UE. In this application, interference also includes interference power or interference plus noise power. Interference experienced by a terminal is correlated in the time, frequency, and spatial domains; for example, changes in interference in the time domain may be related to interference in the frequency or spatial domains, and future interference may be related to past interference. Figure 4 A schematic diagram of interference prediction based on an AI model is shown. (For example...) Figure 4 As shown, the interference prediction module predicts interference based on historically measured interference information to obtain future interference information.

[0086] On the one hand, interference prediction can be performed at the terminal side, meaning the terminal can predict future interference information on a second communication resource based on past interference measurements on a first communication resource. Then, the terminal can report the predicted interference information to the network-side equipment, or optimize the parameters of receiver-related algorithms based on the predicted interference information.

[0087] like Figure 5As shown, interference prediction can be performed on the terminal side. The specific interference prediction process includes:

[0088] S101, the terminal sends interference prediction-related capability information to the network-side equipment.

[0089] S102, the network-side device sends interference measurement configuration information and interference reporting configuration information to the terminal.

[0090] S103, the terminal performs interference measurement based on the interference measurement configuration information to obtain interference measurement information.

[0091] S104, the terminal performs interference prediction based on interference measurement information.

[0092] S105, the terminal sends interference prediction information to the network-side equipment.

[0093] S106, the network-side device sends scheduling information to the terminal.

[0094] It should be understood that S106 is an optional step; for example, the network-side device can send scheduling information to the terminal based on its own implementation.

[0095] On the other hand, interference prediction can be performed on the network side, whereby the terminal reports interference measurements of the first communication resource to the network side. Then, based on the interference measurements reported by the terminal, the network side predicts future interference information of the terminal on the second communication resource, and further determines the air interface resources allocated to the UE for data transmission or signaling transmission based on this information.

[0096] The first and second communication resources may be the same, partially the same, or different, and this is not limited here. The communication resources described in this application can be regarded as a collection of one or more time-domain resources, frequency-domain resources, and spatial-domain resources, and may also be associated with at least one reference signal resource, at least one set of reference signal resources, or at least one reference signal configuration.

[0097] like Figure 6 As shown, interference prediction can be performed on the network side. The specific interference prediction process includes:

[0098] S201, the terminal sends interference prediction capability information to the network-side equipment.

[0099] S202, the network-side device sends interference measurement configuration information and interference reporting configuration information to the terminal.

[0100] S203, the terminal performs interference measurement based on the interference measurement configuration information to obtain interference measurement information.

[0101] S204, the terminal sends interference measurement information to the network-side equipment.

[0102] S205, network-side equipment performs interference prediction based on interference measurement information.

[0103] S206. The network-side device sends scheduling information to the terminal.

[0104] It should be understood that S205 and S206 are optional steps. For example, network-side devices can perform interference prediction or send scheduling information to terminals based on their own implementation.

[0105] Terminals can measure interference using interference measurement resources. Interference measurement resources refer to the communication resources configured by the base station for the UE to measure interference, such as Channel State Information Reference Signal (CSI-RS), Channel State Information for Interference Measurement (CSI-IM), Interference Measurement Resource (IMR), and other reference signal resources that can be used for interference measurement, etc., without specific limitations here. A CSI-RS refers to a reference signal sent by the base station, which the terminal can use to estimate the channel and feed back channel state information to the base station or network node (hereinafter collectively referred to as the base station, which also includes base stations or other network nodes in the access network). A CSI-IM refers to a set of resource elements (REs) reserved for interference measurement. An IMR is a time-frequency resource allocated by the network to the UE for interference measurement. Interference measured by the terminal may be reported to the base station through Channel State Feedback (CSF).

[0106] In relevant protocols, a CSF report typically does not include interference information specific to time, frequency, or spatial resources. Interference information includes, but is not limited to: interference power measured or predicted in a time, frequency, or spatial domain; signal-to-interference-plus-noise ratio (SINR); power level; carrier-to-interference ratio (C / I); and interference covariance information. Interference level is an indicator describing the intensity of interference. In one case, interference levels can be divided into high, medium, and low levels, which can be indicated using 2 bits. Alternatively, interference levels can be divided into levels 1 to 10, with higher values ​​indicating stronger interference. Each level can be associated with a range of interference power or SINR, depending on the device implementation or protocol agreement. Interference covariance information, sometimes called the interference covariance matrix, has diagonal elements describing the interference power information of different receiver branches (e.g., receiver ports); and off-diagonal elements describing the correlation of interference between different receiver branches. In some cases, since the terminal may not be able to distinguish between interference and noise, the interference power may also include interference plus noise power.

[0107] Since the base station is unaware of the interference experienced by the target UE on the target communication resources, it may also be unable to schedule communication resources for the UE based on the interference information from the CSF report. In this case, the serving base station may configure or schedule communication resources with relatively high interference intensity for the UE, which may reduce the signal SINR and thus degrade communication performance, such as increasing the data transmission error rate and latency.

[0108] To enable base stations (including serving base stations or neighboring base stations) to consider the temporal, frequency, and spatial characteristics of interference experienced by the terminal during resource scheduling, the terminal needs to report interference information to the base station, such as measured or predicted values ​​of interference information. This can be a set (or more) of measured or predicted values ​​of interference information (such as interference power or SINR) obtained from at least one interference measurement instance, or a set (or more) of measured or predicted values ​​and their corresponding probabilities. The at least one interference measurement instance can be obtained by the UE on a set of interference measurement resources in the time, frequency, or spatial domains. This set of interference measurement resources may include: one or more CSI-RS, one or more CSI-IM, or one or more IMR. A measured value refers to interference information obtained through at least one interference measurement instance. A predicted value refers to future interference information predicted based on at least one past interference measurement instance.

[0109] The reported interference information may be in the form of a distribution-based representation or a non-distribution-based representation. For a distribution-based representation, the interference distribution reported by the terminal may be a probability density function related to the time, frequency, or spatial domains, or a probability mass function. A probability density function describes the probability of a continuous random variable within a certain range. A probability mass function describes the probability of a discrete random variable equaling certain values. For example, X is a discrete random variable, and its possible range of values ​​is:

[0110] R X ={x1,x2,x3,x4…}.

[0111] Wherein, the probability mass function of X is: P X (x k ) = P(X = x k ), k = 1, 2, 3, 4...

[0112] In one embodiment, the reported interference distribution takes the form of a probability quality function, which describes the measured or predicted values ​​of interference information and their probabilities on a given time, frequency, or spatial resource, i.e.:

[0113] P(IpN=x k |t=t m f = f n ,s=s q );

[0114] k = 1, 2, 3, 4…;

[0115] m = 1, 2, 3, 4…;

[0116] n = 1, 2, 3, 4…;

[0117] q = 1, 2, 3, 4...

[0118] Where, x k This represents the power of the kth interference, such as x1 = -80dBm, x2 = -81dBm, x3 = -82dBm, ...

[0119] t m This represents the m-th time-domain resource, such as t1 = time slot 1, t2 = time slot 2, t3 = time slot 3, ...

[0120] f n This represents the nth frequency domain resource, such as f1 = subband 1, f2 = subband 2, f3 = subband 3, ...

[0121] s qThis represents the q-th spatial resource, such as s1 = beam index 1, s2 = beam index 2, s3 = beam index 3, ...

[0122] In this embodiment, P(IpN=x k |t=t m f = f n ,s=s q This describes the terminal's time-domain resources t. m Frequency domain resources f n and airspace resources q The measured or predicted interference power is x k The probability of.

[0123] Of course, the granularity of time-domain resources, frequency-domain resources, and spatial-domain resources can also be other. For example, time-domain resources can also be orthogonal frequency division multiplexing (OFDM) symbols, subframes, frames, etc., frequency-domain resources can also be physical resource blocks (PRBs) or resource blocks (RBs), and spatial-domain resources can also be physical cells, reference signal resources, ports, etc.

[0124] The probability described in this application can also be replaced by descriptions such as confidence level, accuracy, uncertainty, and uncertainty range. The characteristics are: the larger the value, the higher the probability of occurrence, or the greater the confidence or credibility, or the higher the accuracy, or the lower the uncertainty, or the smaller the uncertainty range.

[0125] In one scenario, the base station may be configured with granularity for interference measurement or prediction, including but not limited to:

[0126] Frequency domain granularity: Interference measurement or prediction is based on the full bandwidth or sub-band (or multiple sub-bands), etc. If the measured or predicted value of an interference information can be associated with the full bandwidth or (one or more) sub-bands, then the measured or predicted value of this interference information describes the interference intensity of the full bandwidth or (one or more) sub-bands.

[0127] Temporal granularity: The interference measurement or prediction is symbol-level interference, slot-level interference, or multiple slot-level interference, etc. For example, if the measured or predicted value of an interference information is slot-level interference, then the measured or predicted value of this interference information describes the interference intensity on one slot.

[0128] Spatial granularity: Base stations may configure multiple reference signal resources or beams for interference measurement or prediction. If the measured or predicted value of an interference information is associated with a specific beam or reference signal resource, then the measured or predicted value of this interference information describes the interference intensity on that beam or reference signal resource.

[0129] It should be noted that in scenarios where a terminal deploys an AI model or algorithm (hereinafter referred to as a model) and performs interference prediction based on that model, the model's performance may be affected by various factors such as neighbor cell scheduling, neighbor cell load, neighbor cell antenna configuration, and changes in the wireless environment. Generally, a model may be associated with one or more network configurations or environments. When the network configuration or environment changes, the model's predictive performance may degrade. This application, by supervising the model's predictive performance, ensures that the terminal can promptly detect and take measures when the model's predictive performance degrades, such as model switching, model activation / deactivation, etc. Furthermore, the terminal may deploy multiple AI models for interference prediction to adapt to different network configurations or environments.

[0130] The wireless communication method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0131] Figure 7 This is a schematic flowchart of a wireless communication method 300 according to an embodiment of this application.

[0132] like Figure 7 As shown, the wireless communication method 300 may include at least some of the following:

[0133] S301, the terminal reports the first information.

[0134] Wherein, the first information is used to indicate at least one of the following:

[0135] The prediction accuracy for T1 interference information is T1≥1;

[0136] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0137] Performance information of artificial intelligence (AI) models.

[0138] For example, the prediction accuracy of the T1 interference information can also be referred to as, or replaced by, the accuracy, confidence level, or validity of the prediction results of the T1 interference information. The prediction accuracy of the T1 interference information includes at least one of the following: the prediction accuracy of each interference information in the T1 interference information, the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of the T1 interference information. The accuracy of any interference information in the T1 interference information can be determined based on the predicted and measured values ​​of that interference information. Optionally, the T1 interference information can be referred to as, or replaced by, T1 prediction results or T1 inference results. For example, the T1 interference information can be the T1 prediction results or inference results output by the AI ​​model. The interference information can be referred to in the description of interference information above; to avoid repetition, it will not be repeated here.

[0139] For example, the T2 time-domain units can be at least one time-domain unit located within a prediction window used for interference information prediction. The interference information within a time-domain unit can include one or more interference information items. The time-domain unit can also be referred to as a time-domain resource unit, and for example, the time-domain unit includes at least one of the following: Orthogonal Frequency Division Multiplexing (OFDM) symbols, time slots, subframes, frames, seconds, milliseconds, time intervals, etc.

[0140] For example, the prediction accuracy of the interference information within the T2 time-domain units can also be referred to as, or replaced by, the accuracy, confidence level, or validity of the prediction results of the interference information associated with the T2 time-domain units. The prediction accuracy of the interference information within the T2 time-domain units includes at least one of the following: the prediction accuracy of the interference information within each of the T2 time-domain units, the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of the interference information within the T2 time-domain units. The prediction accuracy of the interference information within any time-domain unit of the T2 time-domain units can be determined based on the predicted value and measured value corresponding to that any time-domain unit in at least one prediction. The predicted value corresponding to that any time-domain unit can be a predicted value obtained through one or more predictions.

[0141] For example, the performance information of the AI ​​model can also be understood as the performance, adaptability, or effectiveness of the AI ​​model used for interference prediction. The performance information of the AI ​​model is determined based on the predicted and measured values ​​corresponding to each time-domain unit in at least one prediction. Optionally, the performance information of the AI ​​model can be determined based on the prediction accuracy of one or more interference information (e.g., T3 interference information). For example, the performance information of the AI ​​model can be the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of the one or more interference information (e.g., T3 interference information). Optionally, the performance information of the AI ​​model can be determined based on the prediction accuracy of interference information within one or more time-domain units (e.g., T4 time-domain units). For example, the performance information of the AI ​​model can be the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of interference information within one or more time-domain units (e.g., T4 time-domain units).

[0142] For example, the value of T1 or the value of T2 can be indicated by the network-side device or agreed upon by the protocol. Indication by the network-side device can ensure flexibility, while agreement by the protocol can reduce signaling overhead.

[0143] For example, the first information may also be referred to as performance indication information, accuracy indication information, etc.

[0144] In this embodiment, the terminal reports first information used to determine the accuracy of predictions or the performance information of AI models, enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the communication performance of the terminal.

[0145] In some embodiments, the first information includes at least one of the following:

[0146] 1. First indication information, used to indicate the prediction accuracy of the first interference information among the T1 interference information.

[0147] Considering that terminals may implement models differently, such as using regression or classification models to perform interference prediction, the determination of the prediction accuracy of interference information can be implemented by the terminal itself. This reduces signaling overhead and increases terminal implementation flexibility. Alternatively, the network-side device can indicate a first threshold to the terminal to improve the flexibility of judging prediction accuracy. For example, if the difference between the predicted and measured values ​​of interference information is less than or equal to the first threshold, the terminal should consider the prediction accurate; otherwise, the terminal considers the prediction inaccurate.

[0148] Based on interference information from the past N time-domain units, the terminal can predict interference information for the next M² time-domain units. For example, ... Figure 8As shown, N=8, M2=4. In the case of periodic disturbance measurements, as... Figure 9 As shown, after the terminal predicts the interference information for the next four time-domain units based on the measured values ​​of interference information within the past eight time-domain units, it can continue to perform interference measurements to obtain the measured values ​​of interference information within these four time-domain units. Then, by comparing the measured value and the corresponding predicted value for each interference information, the prediction accuracy for each interference information can be obtained. The measured values ​​can also be called measured quantities. For a detailed explanation of the measured values ​​and predicted values, please refer to the description above; to avoid repetition, it will not be repeated here.

[0149] For example, the first interference information is any one of the T1 interference information. For instance, the first information includes T1 first indication information corresponding to the T1 interference information.

[0150] For example, the first information includes: the first indication information corresponding to the first interference information, the first indication information corresponding to the second interference information, ..., the first indication information corresponding to the T1th interference information.

[0151] For example, when the first information includes T1 first indication information corresponding to the T1 interference information, the arrangement order of the T1 first indication information in the first information is the same as the time domain order of the time domain units associated with the T1 interference information.

[0152] For example, the first interference information includes multiple interference information among the T1 interference information. For instance, the first information includes at least one first indication information corresponding to the T1 interference information, and the number of the at least one first indication information is less than or equal to T1.

[0153] 2. The second indication information is used to indicate the prediction accuracy of the interference information in the first time domain unit among the T2 time domain units.

[0154] Considering that terminals may implement models in different ways, such as using regression or classification models to perform interference prediction, the specific determination of the prediction accuracy of interference information within a time-domain unit can be implemented by the terminal, thereby reducing signaling overhead and increasing terminal implementation flexibility; alternatively, the network-side device can indicate a first threshold to the terminal to improve the flexibility of judging prediction accuracy. For example, if the difference between the predicted and measured values ​​of interference information within a time-domain unit is less than or equal to the first threshold, the terminal should consider the prediction accurate; otherwise, the terminal considers the prediction inaccurate.

[0155] Based on interference information from the past N time-domain units, the terminal can predict interference information for the next M² time-domain units. For example, ... Figure 8 As shown, N=8, M2=4. For example, as... Figure 8 As shown, N=8, M2=4. In the case of periodic disturbance measurements, as... Figure 9 As shown, after the terminal predicts the interference information for the next 4 time-domain units based on the measured values ​​of interference information in the past 8 time-domain units, the terminal can continue to perform interference measurements to obtain the measured values ​​of interference information in these 4 time-domain units. Then, by comparing these measured and predicted values ​​with the measured and predicted values ​​of interference information in each time-domain unit, the prediction accuracy of interference information in each time-domain unit can be obtained. The measured values ​​can also be called measured quantities. For a detailed explanation of the measured and predicted values, please refer to the description above; to avoid repetition, it will not be repeated here.

[0156] For example, the first time-domain unit is any one of the T2 time-domain units. For instance, the first information includes T2 second indication information corresponding to the T2 time-domain units.

[0157] For example, the first information includes: second indication information corresponding to the first time domain unit, second indication information corresponding to the second time domain unit, ..., second indication information corresponding to the T2th time domain unit.

[0158] For example, when the first information includes T2 second indication information corresponding to the T2 time domain units, the arrangement order of the T2 second indication information in the first information is the same as the time domain order of the T2 time domain units.

[0159] For example, the first time-domain unit includes multiple time-domain units among the T2 time-domain units. For instance, the first information includes at least one second indication information corresponding to the T2 time-domain units, and the number of the at least one second indication information is less than or equal to T2.

[0160] For example, each of the T2 time-domain units may correspond to multiple frequency-domain units; for example, the granularity of the time-domain unit can be a time slot, and the granularity of the frequency-domain unit can be a sub-band.

[0161] For example, if there are T2 time-domain units and Z frequency-domain units, the first information can be a bit sequence of length T2*Z. If the frequency domain is first and then the time domain, the first to Z bits correspond to the first time-domain unit, and the Z+1 to 2Z bits correspond to the second time-domain unit. The position of the bitmap corresponding to the i-th time-domain unit and the j-th frequency-domain unit is Z*i+j.

[0162] In one implementation, the terminal can report the performance of each frequency domain unit corresponding to each time domain unit through a bit map, which can be either frequency domain first and then time domain, or time domain first and then frequency domain, and the specific form can be agreed upon.

[0163] For example, each of the T2 time-domain units may correspond to one frequency-domain unit; for example, the granularity of the time-domain unit can be a time slot, and the granularity of the frequency-domain unit can be a broadband.

[0164] In one implementation, the terminal can report the performance of each time-domain unit via a bitmap.

[0165] For example, the T2 time-domain units can correspond to a bit sequence of length T2, where the i-th position being 1 indicates that the prediction accuracy of the corresponding time-domain unit is low (e.g., the prediction accuracy is greater than or equal to a preset threshold) or the model is invalid; or, the i-th position being 0 indicates that the prediction accuracy of the corresponding time-domain unit is low (e.g., the prediction accuracy is less than or equal to a preset threshold) or the model is invalid.

[0166] 3. A third indication information, used to indicate at least one of the following: the prediction accuracy of T3 interference information, the prediction accuracy of interference information within T4 time domain units, whether the AI ​​model has failed, T3≥1, T4≥1.

[0167] Considering that terminals may implement models in different ways, such as using regression or classification models to perform interference prediction, the specific method for determining the accuracy of interference information or the prediction of interference information within a time-domain unit depends on the terminal implementation. This can reduce signaling overhead and increase terminal implementation flexibility. One implementation method is that the terminal should determine the accuracy based on the prediction accuracy of all interference information or the prediction accuracy of interference information within all time-domain units, such as the average value, weighted average, maximum value, minimum value, etc. For example, the third indication information is used to indicate a value between 0 and 1; the larger the value, the higher the accuracy of the model's prediction of interference information.

[0168] For example, the third indication information is used to indicate the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of the T1 interference information. Or the third indication information is used to indicate the average, median, weighted average, maximum, minimum, etc., of the prediction accuracy of the interference information within the T2 time-domain units.

[0169] It should be understood that in some embodiments, the first information may include any combination of the first indication information, the second indication information and the third indication information, and this application does not specifically limit this.

[0170] In this embodiment, the network-side device can configure or schedule appropriate communication resources for the terminal based on the first indication information, thereby ensuring the terminal's communication performance, through the first indication information, the second indication information, or the third indication information. Furthermore, the terminal can autonomously select appropriate indication information to report to the network-side device, improving the flexibility of reporting the first information.

[0171] It is worth noting that the first indication information can be associated with one interference measurement instance and / or one interference prediction instance. The second indication information can be associated with one or more interference measurement instances and / or one or more interference prediction instances, and the third indication information can be associated with multiple interference measurement instances and / or multiple interference prediction instances. Specifically, a measurement performed by a receiver (e.g., a terminal) on a reference signal resource used for interference measurement can be considered or referred to as an interference measurement instance; interference prediction by a receiver (e.g., a terminal) on a future reference signal resource used for interference measurement, or on a future time-domain, frequency-domain, or spatial-domain resource containing such a reference signal resource, or on a future communication resource (including time-domain, frequency-domain, or spatial-domain), can be considered or referred to as an interference prediction instance. Optionally, the reference signal resource includes, but is not limited to: CSI-RS resources, CSI-IM resources, or IMR resources.

[0172] In some embodiments, the first indication information is used to indicate at least one of the following (e.g., including at least one of the following):

[0173] The difference between the predicted value and the measured value of the first interference information;

[0174] Is the predicted value of the first interference information accurate?

[0175] For example, the difference between the predicted value and the measured value of the first interference information is the difference obtained by subtracting the measured value from the predicted value, or the difference obtained by subtracting the predicted value from the measured value.

[0176] For example, when the first indication information is used to indicate whether the predicted value of the first interference information is accurate, the value of the first indication information can be a confidence level, or the value of the first indication information can be a value between 0 and 1. When the value of the first indication information is 0, it indicates that it is inaccurate, and when the value of the first indication information is 1, it indicates that it is accurate.

[0177] In this embodiment, by indicating the difference between the predicted value and the measured value of the first interference information, the accuracy of the first indication information can be guaranteed; by indicating whether the predicted value of the first interference information is accurate, the signaling overhead of the first indication information can be reduced.

[0178] In some embodiments, the second indication information is used to indicate at least one of the following (e.g., including at least one of the following):

[0179] 1. The average value of the first difference corresponding to the first time domain unit.

[0180] Wherein, the first difference is the difference between the predicted value and the measured value of the interference information within the first time domain unit.

[0181] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the average value of the first difference corresponding to the first time-domain unit among the multiple time-domain units. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The first difference is the difference obtained by subtracting the measured value from the predicted value, or the difference obtained by subtracting the predicted value from the measured value.

[0182] For example, the first time-domain unit may correspond to one or more interference prediction instances, and each interference prediction instance corresponds to a first difference.

[0183] 2. The average of the absolute values ​​of the first differences corresponding to the first time domain unit.

[0184] Wherein, the first difference is the difference between the predicted value and the measured value of the interference information within the first time domain unit.

[0185] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the average value of the absolute values ​​of the first differences corresponding to the first time-domain units among the multiple time-domain units. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The first difference is either the predicted value minus the measured value, or the measured value minus the predicted value.

[0186] For example, the first time-domain unit may correspond to one or more interference prediction instances, and each interference prediction instance corresponds to a first difference.

[0187] 3. The number of instances with accurate predictions corresponding to the first time-domain unit.

[0188] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the number of accurately predicted instances corresponding to the first time-domain unit among the multiple time-domain units. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The number of accurately predicted instances corresponding to the first time-domain unit can refer to: the number of instances where the predicted value is accurate among the interference prediction instances corresponding to the first time-domain unit, for example, the number of instances where the difference between the predicted value and the measured value of the interference information is greater than or equal to a preset threshold among the interference prediction instances corresponding to the first time-domain unit.

[0189] 4. The ratio of the number of accurately predicted instances corresponding to the first time domain unit to the total number of predicted instances corresponding to the first time domain unit.

[0190] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the ratio of the number of accurately predicted instances corresponding to the first time-domain unit to the total number of predicted instances corresponding to the first time-domain unit. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The ratio of the number of accurately predicted instances corresponding to the first time-domain unit to the total number of predicted instances corresponding to the first time-domain unit can refer to: the ratio of the number of accurately predicted instances among the interference prediction instances corresponding to the first time-domain unit (for example, the number of instances among the interference prediction instances corresponding to the first time-domain unit where the difference between the predicted value and the measured value of the interference information is greater than or equal to a preset threshold) to the total number of predicted instances corresponding to the first time-domain unit.

[0191] 5. The number of instances where the prediction is inaccurate corresponding to the first time-domain unit.

[0192] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the number of instances where the prediction is inaccurate for the first time-domain unit among the multiple time-domain units. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The number of instances where the prediction is inaccurate for the first time-domain unit can refer to the number of instances where the prediction is inaccurate among the interference prediction instances corresponding to the first time-domain unit. For example, among the interference prediction instances corresponding to the first time-domain unit, the number of instances where the difference between the predicted value and the measured value of the interference information is less than or equal to a preset threshold.

[0193] 6. The ratio of the number of inaccurate predictions corresponding to the first time domain unit to the total number of predictions corresponding to the first time domain unit.

[0194] For example, when the AI ​​model is used to predict interference information within multiple future time-domain units, the first information includes multiple second indication information corresponding to the multiple time-domain units. The second indication information is used to indicate the ratio of the number of inaccurate prediction instances corresponding to the first time-domain unit to the total number of prediction instances corresponding to the first time-domain unit. For example, the AI ​​model is used to predict interference information within the 1st, 5th, and 9th future time-domain units; the first time-domain unit can be any of the three time-domain units, for example, the first time-domain unit can be the 1st, 5th, or 9th future time-domain unit. The ratio of the number of inaccurate prediction instances corresponding to the first time-domain unit to the total number of prediction instances corresponding to the first time-domain unit can refer to: the ratio of the number of inaccurate prediction instances among the interference prediction instances corresponding to the first time-domain unit (for example, the number of instances among the interference prediction instances corresponding to the first time-domain unit where the difference between the predicted value and the measured value of the interference information is less than or equal to a preset threshold) to the total number of prediction instances corresponding to the first time-domain unit.

[0195] 7. Whether the prediction instance corresponding to the first time domain unit is accurate.

[0196] For example, when the number of accurately predicted instances in the interference prediction instances corresponding to the first time domain unit (e.g., the number of instances where the predicted value of the interference information in the interference prediction instances corresponding to the first time domain unit is greater than or equal to a preset threshold) is greater than or equal to the number of inaccurately predicted instances in the interference prediction instances corresponding to the first time domain unit (e.g., the number of instances where the predicted value of the interference information in the interference prediction instances corresponding to the first time domain unit is less than or equal to a preset threshold), the second indication information is used to indicate that the prediction instances corresponding to the first time domain unit are accurate. When the number of accurately predicted instances in the interference prediction instances corresponding to the first time domain unit (e.g., the number of instances where the predicted value of the interference information in the interference prediction instances corresponding to the first time domain unit is greater than or equal to a preset threshold) is less than or equal to the number of inaccurately predicted instances in the interference prediction instances corresponding to the first time domain unit (e.g., the number of instances where the difference between the predicted value and the measured value of the interference information in the interference prediction instances corresponding to the first time domain unit is less than or equal to a preset threshold), the second indication information is used to indicate that the prediction instances corresponding to the first time domain unit are inaccurate.

[0197] For example, the second indication information is used to indicate whether each prediction instance corresponding to the first time domain unit is accurate.

[0198] For example, for an interference prediction instance, if the difference between the predicted value and the measured value of the corresponding interference information is less than or equal to a preset threshold, it indicates that the interference prediction instance is accurate or the predicted value of the interference information corresponding to the interference prediction instance is accurate. If the difference between the predicted value and the measured value of the corresponding interference prediction instance is greater than or equal to the preset threshold, it indicates that the interference prediction instance is accurate or the predicted value of the interference information corresponding to the interference prediction instance is inaccurate.

[0199] It should be understood that the number of instances involved in this application can also be understood or replaced as the number of predictions.

[0200] It should be noted that the specific values ​​for the average of the first difference, the number of accurately predicted instances, or the ratio of the number of accurately predicted instances to the total number of predicted instances can be values ​​between 0 and 1. A larger value indicates higher prediction accuracy, and how this value is determined depends on the terminal implementation. Similarly, the specific values ​​for the number of inaccurately predicted instances or the ratio of the number of inaccurately predicted instances to the total number of predicted instances can also be values ​​between 0 and 1. A larger value indicates lower prediction accuracy, and how this value is determined depends on the terminal implementation. When the second indication information is used to indicate whether the predicted instance corresponding to the first time-domain unit is accurate, the value of the second indication information can be a confidence level, or it can be a value between 0 and 1. A value of 0 indicates inaccuracy, and a value of 1 indicates accuracy.

[0201] For example, the second indication information is used to indicate at least one of the following (e.g., including at least one of the following):

[0202] The average of the S first differences corresponding to the first time-domain unit;

[0203] The average of the absolute values ​​of the S first differences corresponding to the first time-domain unit;

[0204] The number of accurately predicted instances among the S interference prediction instances corresponding to the first time-domain unit;

[0205] The ratio of the number of accurately predicted instances among the S interference prediction instances corresponding to the first time domain unit to the total number of prediction instances S corresponding to the first time domain unit;

[0206] The number of instances with inaccurate predictions among the S interference prediction instances corresponding to the first time-domain unit;

[0207] The ratio of the number of inaccurate prediction instances among the S interference prediction instances corresponding to the first time domain unit to the total number of prediction instances S corresponding to the first time domain unit;

[0208] Whether the S interference prediction instances corresponding to the first time-domain unit are accurate.

[0209] The S first differences include the differences between the predicted and measured values ​​of interference information within the first time-domain unit in the S predictions. Optionally, S ≥ 1, and the value or minimum value of S can be determined by protocol, indicated by the network-side device to the terminal, or indicated by the terminal to the network-side device; alternatively, the value or minimum value of S can be determined by the terminal based on implementation. Indication by the network-side device ensures flexibility, while protocol agreement reduces signaling overhead. Defining the minimum value of S ensures the accuracy of the second indication information.

[0210] For example, the terminal determines the prediction accuracy of interference information within each time-domain unit based on the statistical results of S model supervision. For the i-th time-domain unit in T2 time-domain units, the specific form indicated by its corresponding second indication information may include at least one of the following: the number of accurately predicted instances, the ratio of the number of accurately predicted instances divided by the total number of instances S, the number of inaccurately predicted instances, or the ratio of the number of inaccurately predicted instances divided by the total number of instances S. Optionally, the number of accurately predicted instances, or the ratio of the number of accurately predicted instances divided by the total number of instances S, can be quantized, for example, to a number between {0, 0.1, ..., 0.9, 1}, where a larger value indicates higher prediction accuracy. Optionally, the number of inaccurately predicted instances, or the ratio of the number of inaccurately predicted instances divided by the total number of instances S, can also be quantized, for example, to a number between {0, 0.1, ..., 0.9, 1}, where a larger value indicates lower prediction accuracy.

[0211] For example, the average of the absolute values ​​of the S first differences can be calculated according to the following formula:

[0212]

[0213] Where i represents the i-th time-domain unit among T2 time-domain units, e i e represents the prediction accuracy of the interference information within the i-th time-domain unit. i It can reflect the true deviation of the predicted value from the measured value, such as e. i A value greater than 0 indicates that the predicted value is smaller than the measured value on average; e i A value less than 0 indicates that the predicted value is, on average, larger than the measured value. i I represents the total number of predicted instances of interference information within the i-th time-domain unit. i,s This represents the measured value of the interference information within the i-th time-domain unit in the s-th prediction. This represents the predicted value of the interference information within the i-th time-domain unit in the s-th prediction. This represents the first difference corresponding to the s-th prediction.

[0214] For example, the average of the absolute values ​​of the S first differences can be calculated according to the following formula:

[0215]

[0216] Where i represents the i-th time-domain unit among T2 time-domain units, e i e represents the prediction accuracy of the interference information within the i-th time-domain unit. i It can reflect the absolute deviation of the predicted value from the measured value. iI represents the total number of predicted instances of interference information within the i-th time-domain unit. i,s This represents the measured value of the interference information within the i-th time-domain unit in the s-th prediction. This represents the predicted value of the interference information within the i-th time-domain unit in the s-th prediction. This represents the first difference corresponding to the s-th prediction.

[0217] In this embodiment, by indicating the average value of the first difference, the number of accurately predicted instances, the number of inaccurately predicted instances, the ratio of the number of accurately predicted instances to the total number of predicted instances, the ratio of the number of inaccurately predicted instances to the total number of predicted instances, and whether the predicted instances are accurate, not only can the accuracy of the second indication information be guaranteed, but the signaling overhead of the second indication information can also be reduced. Furthermore, considering the inherent suddenness and randomness of the wireless communication environment, a single comparison result may lead to frequent ping-pong handover models. Therefore, S predictions are required over a period of time. In this embodiment, the prediction accuracy of the interference information within any time domain unit can be determined based on the predicted and measured values ​​of the interference information within any time domain unit in the S predictions, which can reduce the probability of ping-pong handover models and thus improve communication performance. Of course, in other alternative embodiments, the second indication information can be used to indicate the weighted average, maximum, or minimum value of the first difference, or to indicate the weighted average, maximum, or minimum value of the absolute value of the first difference.

[0218] In some embodiments, the third indication information is used to indicate at least one of the following (e.g., including at least one of the following):

[0219] The average, weighted average, maximum, or minimum value of the second difference;

[0220] The average, weighted average, maximum, or minimum of the third difference;

[0221] Wherein, the second difference is the difference between the predicted value and the measured value of the interference information in the T3 interference information, and the third difference is based on the difference between the predicted value and the measured value of the interference information in the time domain unit in the T4 time domain units.

[0222] For example, the second difference or the third difference is the difference obtained by subtracting the measured value from the predicted value, or the difference obtained by subtracting the predicted value from the measured value.

[0223] In this embodiment, by indicating the calculated value of the second difference or the calculated value of the third difference, not only can the accuracy of the third indication information be guaranteed, but the signaling overhead of the third indication information can also be reduced.

[0224] In some embodiments, prior to S301, the method 300 further includes:

[0225] The terminal predicts interference information based on N time-domain units, or predicts interference information in M1 time-domain units, where N≥1, M1≥T1, and M2≥T2.

[0226] For example, M1 > T1, or M2 > T2.

[0227] For example, such as Figure 8 As shown, the terminal predicts the interference information in the next 4 time domains based on the interference information in the past 8 time domains.

[0228] In this embodiment, associating the first information with the prediction can link supervision and prediction, thereby reducing the signaling overhead of the reference signal.

[0229] In some embodiments, the T1 interference information includes one of the following: the first T1 interference information in the M1 interference information, the T1 interference information indicated by the network-side device in the M1 interference information, the T1 interference information determined by the terminal in the M1 interference information, and T1 interference information at equal intervals in the M1 interference information, where M1 > T1.

[0230] For example, the terminal reports the prediction accuracy of T1 interference information out of M1 interference information. For instance, if M1 = 4, the terminal predicts 4 interference information. If T1 = 3, the T1 interference information can be the first, second, and third interference information, or the T1 interference information includes the first, second, and fourth interference information.

[0231] In one implementation, the T1 interference information items are the first T1 interference information items out of M1 interference information items, where T can be determined by network indication or protocol agreement, or by the terminal based on the implementation. For example, the network-side device can construct an error propagation model based on the prediction accuracy of the first T1 interference information items to predict the prediction accuracy of the subsequent M1-T1 interference information items. Since the prediction accuracy of interference information items whose prediction time is further away from the initial prediction time in the M1 interference information items is worse, reporting the prediction accuracy of the first T1 interference information items can not only ensure the accuracy of the first information, but also reduce the reporting overhead.

[0232] In another implementation, the T1 interference information items are any of the M1 interference information items, specifically indicated by the network-side device through a bitmap or determined by the terminal based on its implementation. If determined by the terminal implementation, the terminal needs to indicate the T1 interference information items to the network-side device. For example, taking the network-side device indicating through a bitmap, assuming M1 = 4, if the bitmap indicated by the network-side device is {1, 1, 0, 0}, it indicates that the interference information items the terminal needs to report for prediction accuracy include the first and second interference information items. By reporting the prediction accuracy of arbitrary interference information, the flexibility of information reporting can be improved.

[0233] In another implementation, the T1 interference messages are T1 equally spaced interference messages out of M1 interference messages. For example, assuming M1 = 4, meaning the terminal predicts 4 interference messages, the T1 interference messages may include the 1st and 3rd interference messages, or the T1 interference messages may include the 2nd and 4th interference messages. For interference messages with intermediate intervals, the network-side device can obtain their prediction accuracy through interpolation or prediction. Optionally, the network-side device can indicate an offset value and a period value to the terminal, such as {0, 2}, where the offset value is 0 and the period is 2 interference messages.

[0234] In this embodiment, by reporting the accuracy of some interference information in M1 interference information, not only can the network-side device configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the communication performance of the terminal, but the signaling overhead of the first information can also be reduced.

[0235] In some embodiments, the T2 time-domain units include one of the following: the first T2 time-domain units in the M2 time-domain units, the T2 time-domain units indicated by the network-side device in the M2 time-domain units, the T2 time-domain units determined by the terminal in the M2 time-domain units, and the T2 time-domain units that are equally spaced in the M2 time-domain units, where M2 > T2.

[0236] For example, the terminal reports the prediction accuracy of interference information within T2 time-domain units out of M2 time-domain units. For instance, if M2 = 4, the terminal predicts interference information within 4 time-domain units. If T2 = 3, the T2 time-domain units can be the first, second, and third time-domain units, or the T2 time-domain units can include the first, second, and fourth time-domain units.

[0237] In one implementation, the T2 time-domain units refer to the first T2 time-domain units out of M2 time-domain units, where T2 can be determined by network indication or protocol agreement, or by the terminal based on its implementation. For example, the network-side device can construct an error propagation model based on the prediction accuracy of interference information within the first T2 time-domain units to predict the prediction accuracy of interference information within the subsequent M2-T2 time-domain units. Since the prediction accuracy of time-domain units whose prediction time is further from the initial prediction time is worse, reporting the prediction accuracy of interference information within the first T2 time-domain units not only ensures the accuracy of the first information but also reduces reporting overhead.

[0238] In another implementation, the T2 time-domain units are any of the M2 time-domain units, specifically indicated by the network-side device through a bitmap or determined by the terminal based on its implementation. If determined by the terminal implementation, the terminal needs to indicate the T2 time-domain units to the network-side device. For example, taking the network-side device indicating through a bitmap, assuming M2 = 4, if the bitmap indicated by the network-side device is {1, 1, 0, 0}, the time-domain units used to indicate that the terminal needs to report the prediction accuracy include the first and second time-domain units. By reporting the prediction accuracy of interference information within any time-domain unit, the flexibility of information reporting can be improved.

[0239] In another implementation, the T2 time-domain units are T2 equally spaced time-domain units out of M2 time-domain units. For example, assuming M2 = 4, meaning the terminal predicts interference information within 4 time-domain units, the T2 time-domain units may include the 1st and 3rd time-domain units, or the T2 time-domain units may include the 2nd and 4th time-domain units. For intermediate time-domain units, the network-side device can obtain the prediction accuracy of the interference information within them through interpolation or prediction. Optionally, the network-side device can indicate an offset value and a period value to the terminal, such as {0, 2}, where the offset value is 0 and the period is 2 time-domain units.

[0240] In this embodiment, by reporting the accuracy of interference information within some time-domain units in M2 time-domain units, not only can the network-side device configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the communication performance of the terminal, but the signaling overhead of the first information can also be reduced.

[0241] In some embodiments, prior to S301, the method 300 further includes:

[0242] The terminal receives at least one first reporting configuration information, which is used by the terminal to determine or report interference information predicted by the terminal.

[0243] For example, the reference signal resources configured in the first reporting configuration information are used by the terminal to determine or report the interference information predicted by the terminal.

[0244] In this embodiment, by receiving at least one first reported configuration information, the terminal is able to determine or report the interference information predicted by the terminal. Since the interference information predicted by the terminal can be used to assist the network-side device in configuring or scheduling appropriate communication resources for the terminal, the communication performance of the terminal can be guaranteed.

[0245] In some embodiments, the first reporting configuration information is further used by the terminal to determine or report the first information.

[0246] For example, the first reported configuration information is used to configure two reference signal resources, such as a first reference signal resource and a second reference signal resource. The first reference signal resource is used by the terminal to determine or report interference information predicted by the terminal, and the second reference signal resource is used by the terminal to determine or report the first information. In other words, the first reference signal resource is used for model inference, and the second reference signal resource is used for model supervision. Model inference refers to the process of predicting future interference information, and model supervision refers to the process of determining the applicability of the model used for interference prediction.

[0247] For example, when the first reported configuration information is used to configure two reference signal resources, the first reference signal resource and the second reference signal resource can be distinguished by an identifier, or the first reference signal resource and the second reference signal resource can be distinguished in sequence. For example, the first reference signal resource configured by the first reported configuration information is the first reference signal resource, and the second reference signal resource configured by the first reported configuration information is the second reference signal resource.

[0248] In this embodiment, the reference signal resources used for model supervision and the reference signal resources used for model inference are configured with the same first reporting configuration information, which can improve the configuration efficiency of information.

[0249] In some embodiments, prior to S301, the method 300 further includes:

[0250] The terminal receives second reporting configuration information, which is associated with at least one first reporting configuration information. The second reporting configuration information is used by the terminal to determine or report the first information, and the first reporting configuration information is used by the terminal to determine or report the interference information predicted by the terminal.

[0251] For example, the reference signal resources configured in the first reporting configuration information are used by the terminal to determine or report the interference information predicted by the terminal. The reference signal resources configured in the second reporting configuration information are used by the terminal to determine or report the first information. In other words, the reference signal resources configured in the first reporting configuration information are used for model inference, and the reference signal resources configured in the second reporting configuration information are used for model supervision. Model inference refers to the process of predicting future interference information, and model supervision refers to the process of determining the applicability, accuracy, or effectiveness of the model used for interference prediction.

[0252] In this embodiment, the reference signal resources used for model supervision and the reference signal resources used for model inference are configured with different reporting configuration information, so that the network-side device can configure the second configuration information in real time according to the needs, which can improve the flexibility of information configuration.

[0253] In some embodiments, the second reported configuration information is associated with at least one first reported configuration information, including at least one of the following:

[0254] The second reported configuration information is the identification information of the reference signal resource configuration that is associated with the first reported configuration information;

[0255] The second reported configuration information is associated with the same reference resource identifier information as the first reported configuration information;

[0256] The second reported configuration information includes the identification information of the first reported configuration information.

[0257] For example, when the second reported configuration information is associated with the same reference signal resource configuration identifier information as the first reported configuration information, the reference resource configured in the second reported configuration information is the same as the reference signal resource configured in the first reported configuration information.

[0258] For example, the reference signal resource configured in the first reported configuration information includes a first reference resource, and the reference signal resource configured in the second reported configuration information includes a second reference resource. When the second reported configuration information is associated with the same reference resource identifier information as the first reported configuration information, the first reference resource and the second reference resource are the same.

[0259] For example, the second reporting configuration information is associated with at least one configured first reporting configuration information to reduce the possibility that the second reporting configuration information received by the terminal is associated with an unconfigured first reporting configuration information, thereby ensuring the configuration efficiency of the configuration information; for example, the first reporting configuration information associated with the second reporting configuration information is received or configured before the second reporting configuration information, or configured at a specific time. In another implementation, the second reporting configuration information may be associated with an unconfigured or unreceived first reporting configuration information; optionally, the terminal caches the second reporting configuration information until the first reporting configuration information is received. Optionally, the terminal discards or ignores the second reporting configuration information.

[0260] In this embodiment, the second reported configuration information is associated with the at least one first reported configuration information by means of the resource configuration identifier, reference resource identifier information and the identifier information of the reported configuration information, so that the terminal can reasonably determine the first information based on the associated second reported configuration information and the at least one first reported configuration information, thereby improving the determination efficiency of the first information.

[0261] In some embodiments, the second reporting configuration information is used to configure the reporting period of the first information.

[0262] In this embodiment, when the second reporting configuration information is used to configure the reporting period of the first information, the terminal can report the first information according to the configured reporting period. The network-side device can obtain the first information in a timely manner, thereby enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the timely obtained first information, which can ensure the communication performance of the terminal.

[0263] In some embodiments, the first reporting configuration information is used to configure the reporting period of the interference information predicted by the terminal.

[0264] In this embodiment, when the first reporting configuration information is used to configure the reporting period of the interference information predicted by the terminal, the terminal can report the interference information predicted by the terminal according to the configured reporting period. The network-side device can obtain the interference information predicted by the terminal in a timely manner, thereby enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the timely obtained interference prediction, which can ensure the communication performance of the terminal.

[0265] In some embodiments, S301 includes:

[0266] The terminal periodically reports the first information;

[0267] The reporting period for the first information satisfies one of the following:

[0268] 1. The reporting period of the first information is determined based on the reporting period of the interference information predicted by the terminal.

[0269] For example, the reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal. When the reporting period of the first information is greater than the reporting period of the interference information predicted by the terminal, the reporting overhead of the first information can be reduced compared to the reporting of the predicted interference information. When the reporting period of the first information is equal to the reporting period of the interference information predicted by the terminal, the network side can obtain the performance of the interference prediction model or the accuracy of the interference prediction more timely, thereby ensuring the rationality of the network side's scheduling. In one case, the reporting period of the first information is determined according to the reporting period of the interference information predicted by the terminal. The terminal can report the first information and the predicted interference information in the same CSI feedback report, for example, on the same PUCCH or PUSCH resources or at the same reporting time, thereby reducing the reporting overhead of the first information.

[0270] For example, if the interference information predicted by the terminal is reported periodically or semi-persistently (also known as semi-statically), and the reporting period is T... p The period during which the terminal reports the first information is based on T. p Confirmed. For example, the period for the terminal to report the first information is T. p ×U1. T p The determination is made by the terminal based on the implementation or network indication.

[0271] In one implementation, U1 = S, and S ≥ 1.

[0272] In one implementation, U1 = 1.

[0273] 2. The reporting period of the first information is determined according to the reporting period of the Channel State Information (CSI).

[0274] For example, the reporting period of the first information is greater than or equal to the reporting period of CSI. When the reporting period of the first information is greater than the reporting period of CSI, the reporting overhead of the first information can be reduced compared to CSI reporting. When the reporting period of the first information is equal to the reporting period of CSI, the network side can obtain the performance of the terminal-side interference prediction model or the accuracy of interference prediction more timely, thereby ensuring the rationality of network-side scheduling. In one case, the reporting period of the first information is determined according to the reporting period of CSI, and the terminal can report the first information in the CSI feedback report, for example, on the same PUCCH or PUSCH resources or at the same reporting time, thereby reducing the reporting overhead of the first information.

[0275] For example, if CSI is reported periodically or semi-persistently (also known as semi-statically), and the reporting period is T CSI The period during which the terminal reports the first information is based on T. CSI Confirmed. For example, the period for the terminal to report the first information is T. CSI ×U2. T CSI The determination is made by the terminal based on the implementation or network indication.

[0276] In one implementation, U2 = S.

[0277] In one implementation, U2 = 1.

[0278] 3. The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal.

[0279] For example, such as Figure 10 As shown, the reporting period of the first information is equal to the reporting period of the interference information predicted by the terminal.

[0280] 4. The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal.

[0281] 5. The first reporting period of the first information, the first reporting period of the relative channel state information (CSI), or the first reporting period of the interference information predicted by the terminal has a first offset value.

[0282] For example, the first offset value may be agreed upon by the protocol, indicated by the network-side device, or determined by the terminal.

[0283] 6. In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

[0284] For example, the second offset value may be agreed upon by the protocol, indicated by the network-side device, or determined by the terminal.

[0285] Of course, the reporting period of the first information can be determined by the terminal, indicated by the network-side device, or agreed upon by the protocol, and this application does not make any specific limitation on this.

[0286] In this embodiment, by periodically reporting the first information, the network-side device can obtain the first information in a timely manner, thereby enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the timely obtained first information, which can ensure the communication performance of the terminal.

[0287] In some embodiments, the first offset value includes one or more reporting periods of the interference information predicted by the terminal; or

[0288] The first offset value includes one or more reporting periods of the first information; or

[0289] At least one of the first offset value, the maximum value of the first offset value, and the minimum value of the first offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0290] For example, such as Figure 11 As shown, the first offset value may include two reporting cycles of the interference information predicted by the terminal.

[0291] For example, such as Figure 12 As shown, the first offset value may include one reporting cycle of the first information.

[0292] For example, when the first offset value, the maximum value of the first offset value, or the minimum value of the first offset value is determined by the terminal, it can be determined based on the time length of the prediction window of the interference information.

[0293] In this embodiment, by refining the method for determining the first offset value, the terminal can choose a suitable method to determine the first offset value according to actual needs or its own capabilities, thereby improving the flexibility of determining the first offset value. Furthermore, determining the first offset value through a protocol-agreed method can reduce the signaling overhead introduced for determining the first offset value.

[0294] In some embodiments, the second offset value is determined based on at least one of the following: the reporting period of the first information, the SFN of the system frame used to report the first information, the number of time-domain units included in the SFN used to report the first information, and the index of the time-domain unit used to report the first information; or, at least one of the second offset value, the maximum value of the second offset value, and the minimum value of the second offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0295] For example, the relationship between the second offset value and at least one of the following is agreed upon by a protocol: the reporting period of the first information, the SFN of the system frame used to report the first information, the number of time-domain units included in the SFN used to report the first information, and the index of the time-domain unit used to report the first information.

[0296] For example, the second offset value can be determined according to the following formula:

[0297]

[0298] in, n represents the number of time slots included in the system frame (frame) used to report the first information, where the Numerology is configured as u. f This indicates the SystemFrame number (SFN) of the system frame used to report the first information. T represents the slot index in the system frame (frame) configured with Numerology as u, used for reporting the first information. offset_1 T represents the second offset value. m This indicates the reporting period for the first piece of information.

[0299] In this embodiment, by refining the method for determining the second offset value, the terminal can choose a suitable method to determine the second offset value according to actual needs or its own capabilities, thereby improving the flexibility of determining the second offset value. Furthermore, determining the second offset value through a protocol-agreed method can reduce the signaling overhead introduced for determining the second offset value.

[0300] In some embodiments, the first information and the interference information predicted by the terminal are reported through a Channel State Information (CSI) feedback report; or, the first information is reported through Media Access Control (MAC) layer signaling or Radio Resource Control (RRC) signaling, and the interference information predicted by the terminal is reported through a Channel State Information (CSI) feedback report; or, the first information is sent through a deactivation request message or a deactivation notification message, wherein the deactivation request message is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period, and the deactivation notification message is used to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model is deactivated or that the AI ​​model is unavailable within a target time period.

[0301] For example, by agreeing on a protocol, the first information and the interference information predicted by the terminal can be reported through the same CSI feedback report, which can reduce the reporting overhead of the first information.

[0302] For example, when the first information and the interference information predicted by the terminal are reported through two CSI feedback reports, the reporting period of the first information and the reporting period of the interference information predicted by the terminal may be aligned or may not be aligned. In one case, if the network instructs the terminal to report the first information and the predicted interference information through two CSI feedback reports, and the timing of their reporting conflicts (e.g., the timing is the same or partially overlaps), then they can be merged into the same CSI feedback report. For example, the first information has a lower priority than the predicted interference information; if the network instructs the terminal to report the first information and the predicted interference information through two CSI feedback reports, and the timing of their reporting conflicts (e.g., the timing is the same or partially overlaps), then the terminal prioritizes discarding the first information.

[0303] For example, the first information and the interference information predicted by the terminal can be reported through the same CSI feedback report or two different CSI feedback reports.

[0304] For example, when the first information is reported via deactivation request information or deactivation notification information, it can be carried in the deactivation request information or deactivation notification information, or the first information can be implicitly indicated through the deactivation request information or deactivation notification information to reduce the reporting overhead of the first information. For instance, if the terminal reports deactivation request information or deactivation notification information, it can implicitly indicate that the prediction accuracy of the T1 interference information is less than or equal to a preset threshold, the prediction accuracy of the interference information in the T2 time domain units is less than or equal to a preset threshold, or the AI ​​model has failed.

[0305] For example, the first information is reported through Layer 1 or the Media Access Control (MAC) layer to improve the flexibility of the reporting method of the first information.

[0306] In this embodiment, when the first information and the interference information predicted by the terminal are reported through the same report, or when the first information is reported through a deactivation request or deactivation notification, it not only facilitates terminal implementation but also reduces parameter indications related to reporting, thereby lowering the reporting overhead of the first information. When the first information and the interference information predicted by the terminal are reported through different reports, it not only improves the flexibility of the terminal in reporting the first information but also helps network-side devices process the interference information predicted by the terminal and the first information separately, thereby reducing the processing complexity of the network-side devices.

[0307] In some embodiments, S301 includes:

[0308] If the first condition is met, the terminal reports the first information;

[0309] The first condition includes at least one of the following:

[0310] The terminal receives information to trigger the terminal to report the first information;

[0311] The prediction accuracy of the T1 interference information meets the reporting trigger condition;

[0312] The prediction accuracy of the interference information within the T2 time-domain units meets the reporting triggering condition;

[0313] The performance information meets the reporting trigger conditions;

[0314] The serving cell of the terminal has changed;

[0315] The bandwidth part (BWP) or the active BWP of the terminal changes.

[0316] For example, the network-side device can trigger the terminal to report the first information. For instance, after receiving information to trigger the terminal to report the first information, the terminal reports the first information. In one implementation, the network-side device triggers the terminal to report the first information in the CSI reporting configuration.

[0317] For example, the terminal can trigger the terminal to report the first information. For instance, the terminal is triggered to report the first information when a reporting trigger condition is met. In one implementation, the terminal actively reports the first information when the prediction accuracy of T1 interference information is less than or equal to a preset threshold, the prediction accuracy of interference information within T2 time-domain units is less than or equal to a preset threshold, or the AI ​​model fails.

[0318] For example, the reporting trigger condition for the T1 interference information includes: the prediction accuracy of the T1 interference information is less than or equal to a preset threshold. For instance, the reporting trigger condition for the T1 interference information includes: the average, weighted average, maximum, or minimum value of the prediction accuracy of the T1 interference information is less than or equal to a preset threshold.

[0319] For example, the reporting triggering condition for the T2 time-domain units includes: the prediction accuracy of the interference information within the T2 time-domain units is less than or equal to a preset threshold. For instance, the reporting triggering condition for the T2 time-domain units includes: the average, weighted average, maximum, or minimum value of the prediction accuracy of the interference information within the T2 time-domain units is less than or equal to a preset threshold.

[0320] For example, the reporting trigger conditions for the performance information include: the prediction accuracy of the T3 interference information is less than or equal to a preset threshold, or the prediction accuracy of the interference information within the T4 time-domain units is less than or equal to a preset threshold. Alternatively, the reporting trigger conditions for the performance information include: the average, weighted average, maximum, or minimum value of the prediction accuracy of the T3 interference information is less than or equal to a preset threshold, or the average, weighted average, maximum, or minimum value of the prediction accuracy of the interference information within the T4 time-domain units is less than or equal to a preset threshold.

[0321] For example, if the serving cell of the terminal changes, or the BWP or activated BWP of the terminal changes, it indicates that the network environment or network configuration information of the terminal has changed. In this case, the predictive performance of the AI ​​model may decrease, leading to the terminal predicting and reporting interference information with low accuracy. If the network-side device schedules communication resources for the terminal based on inaccurate interference information, it will reduce the terminal's communication performance. In this embodiment, when the serving cell of the terminal changes, or the BWP or activated BWP of the terminal changes, the terminal is triggered to report the first information. This allows the network-side device to configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the terminal's communication performance. Alternatively, the interference prediction reporting on the terminal side can be deactivated, thereby reducing reporting overhead.

[0322] In this embodiment, when the terminal receives information triggering it to report the first information, the terminal reports the first information, enabling network-side devices to trigger the terminal to report the first information based on actual needs, thus improving the reporting flexibility of the first information. When the reporting triggering conditions are met, the terminal reports the first information, reducing the signaling overhead of triggering the reporting of the first information. When the terminal's serving cell changes, or when the terminal's BWP or active BWP changes, the terminal is triggered to report the first information. Even if the interference information predicted and reported by the terminal is of low accuracy, by reporting the first information, the network-side devices can configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the terminal's communication performance.

[0323] In some embodiments, the first information is associated with at least one of the following: a first transmission configuration indication (TCI) state, the receiving beam of the terminal, and the receiving port of the terminal; wherein the first TCI state or the receiving beam is determined according to at least one of the following: a TCI state associated with a reference signal for interference measurement, or a TCI state activated by a Media Access Control (MAC) Control Element (CE).

[0324] For example, the first TCI state includes at least one of the following: at least one TCI state associated with a reference signal for interference measurement, at least one TCI state indicated by a transmission configuration activated by MAC-CE, and at least one of the intersections of the TCI state associated with the reference signal for interference measurement and the TCI state indicated by a transmission configuration activated by MAC-CE. For example, the first TCI state is a TCI state associated with the reference signal for interference measurement and activated by MAC-CE.

[0325] In one implementation, the terminal reports the first information associated with the first TCI state. The advantage is that this informs the network-side device about the performance of the interference prediction model under the first TCI state. Knowing this more granular information, the network-side device can activate or configure communication resources that meet the terminal model's requirements. The first TCI state may include one or more TCI states, or the first TCI state may include one or more TCI state groups. That is, the first information can be information associated with one TCI state, multiple TCI states, one TCI state group, or multiple TCI state groups. The multiple TCI states or the one TCI state group may be associated with multiple serving cells and / or multiple interfering cells; this application does not specifically limit this.

[0326] In one implementation, the terminal reports the first information associated with its received beam. The advantage is that this informs the network-side device about the performance of the interference prediction model under the terminal's received beam. Knowing this more detailed information, the network can activate or configure settings that meet the terminal model's requirements. The terminal's received beam may include one beam, multiple beams, a beam pair, a set of beam pairs, a beam set, or multiple beam sets; this application does not specifically limit this.

[0327] In one implementation, the terminal reports the first information associated with its receiving port. This has the advantage of informing the network-side device about the performance of the interference prediction model at the terminal's receiving port. Knowing this more detailed information, the network can activate or configure settings that meet the terminal model's requirements. The terminal's receiving port can include one port, multiple ports, a pair of ports, a set of port pairs, a collection of ports, or multiple collections of ports; this application does not specifically limit this.

[0328] For example, the terminal may report first information corresponding to at least one TCI state, first information corresponding to at least one receiving beam, and first information corresponding to at least one receiving port. Optionally, the first TCI state is any TCI state among the at least one TCI states. For example, taking the at least one TCI state as an example, the first information corresponding to the at least one TCI state includes:

[0329] TCI state 1 and its associated first information 1;

[0330] TCI state 2 and its associated first information 2; ...

[0332] TCI state K and its associated first information K.

[0333] For example, different first information can be associated with the same or different TCI states, different first information can be associated with the same or different receiving beams of the terminal, and different first information can be associated with the same or different receiving ports of the terminal.

[0334] In this embodiment, by reporting the first TCI status, the first information associated with the receiving beam or receiving port, the network-side device can activate or configure a configuration that meets the requirements of the terminal model, thereby ensuring the predictive performance of the model as much as possible or reducing the switching frequency of the model.

[0335] In some embodiments, the first information includes at least one of the following:

[0336] The TCI status associated with the first information;

[0337] The TCI state associated with each of the T1 interference messages;

[0338] The Transmission Configuration Indicator (TCI) status associated with each of the T2 time-domain units;

[0339] The transmission configuration associated with the AI ​​model indicates the TCI status;

[0340] The receiving beam or receiving port associated with the first information;

[0341] The receiving beam or receiving port associated with each of the T1 interference information;

[0342] The receiving beam or receiving port associated with each of the T2 time-domain units;

[0343] The AI ​​model is associated with a receiving beam or receiving port.

[0344] For example, when a terminal reports the first information, it may refer to the reporting granularity of the prediction accuracy and report its associated TCI status, the terminal's receiving beam, or the terminal's receiving port.

[0345] For example, when the first information includes the TCI state associated with the first information, all interference information in the T1 interference information or all time domain units in the T2 time domain units are associated with the same TCI state. When the first information includes the TCI state associated with each interference information in the T1 interference information, different interference information in the T1 interference information are associated with the same or different TCI states. When the first information includes the TCI state associated with each time domain unit in the T2 time domain units, different time domain units in the T2 time domain units are associated with the same or different TCI states. The associated TCI state may include one TCI state, multiple TCI states, one TCI state group, or multiple TCI state groups.

[0346] For example, the first information can be agreed through a protocol to include the TCI state associated with the first information, that is, the protocol agrees that all interference information in the T1 interference information or all time domain units in the T2 time domain units are associated with the same TCI state.

[0347] For example, when the first information includes the receiving beam / receiving port associated with the first information, all interference information in the T1 interference information or all time domain units in the T2 time domain units are associated with the same receiving beam / receiving port. When the first information includes the receiving beam / receiving port associated with each interference information in the T1 interference information, different interference information in the T1 interference information are associated with the same or different receiving beams / receiving ports. When the first information includes the receiving beam / receiving port associated with each time domain unit in the T2 time domain units, different time domain units in the T2 time domain units are associated with the same or different receiving beams / receiving ports. The associated receiving beam / receiving port can be one receiving beam / receiving port, multiple receiving beams / receiving ports, one group of receiving beams / receiving ports, or multiple groups of receiving beams / receiving ports.

[0348] For example, the protocol can stipulate that the first information includes the receiving beam / receiving port associated with the first information, that is, the protocol stipulates that all interference information in the T1 interference information or all time domain units in the T2 time domain units are associated with the same receiving beam / receiving port.

[0349] In this embodiment, when the terminal reports the first information, it can refer to the reporting granularity of the prediction accuracy and report its associated TCI status, the terminal's receiving beam, or the terminal's receiving port, so that the network-side device can activate or configure a configuration that meets the terminal model's requirements, thereby ensuring the model's prediction performance as much as possible or reducing the model's switching frequency.

[0350] In some embodiments, the method 300 further includes at least one of the following:

[0351] Receive deactivation instruction information, which is used to instruct the terminal to deactivate the AI ​​model, or to instruct the terminal to deactivate the AI ​​model within a target time period;

[0352] Send a deactivation request message to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period;

[0353] Deactivate the AI ​​model;

[0354] Send a deactivation notification message to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model will be unavailable within a target time period.

[0355] During the target time period for deactivating the AI ​​model, the AI ​​model is retrained.

[0356] Send an update request message to request an update to the AI ​​model.

[0357] For example, after reporting the first information, the terminal receives a deactivation instruction and then deactivates the AI ​​model. Optionally, the terminal retrains the AI ​​model during the deactivation period.

[0358] For example, after reporting the first information, the terminal sends a deactivation request, then receives a deactivation instruction, and deactivates the AI ​​model. Optionally, the terminal retrains the AI ​​model during the deactivation period.

[0359] For example, the terminal deactivates the AI ​​model and then sends a deactivation notification. Alternatively, the terminal sends a deactivation notification and then deactivates the AI ​​model. Optionally, the terminal retrains the AI ​​model during the period when the AI ​​model is deactivated.

[0360] For example, the terminal sends an update request message and receives an update indication message, the update indication message being used to indicate the target model to be updated.

[0361] For example, after the terminal measures or reports the first information, it may perform the following actions:

[0362] Behavior 1: Deactivation / Model Switching / Rollback.

[0363] If the terminal's model supervision results indicate that the model has failed, the terminal may perform at least one of the following:

[0364] The terminal reports the first information to the network-side device, for example, through a deactivation request or deactivation notification. Upon receiving the first information from the terminal, the network-side device instructs whether to deactivate the AI ​​model or specifies a timer or time period for deactivating the AI ​​model. In one case, candidate values ​​for the timer or time period include {20ms, 50ms, 100ms, 200ms, 1000ms, 2000ms, ...}, or other candidate values, which are not limited here.

[0365] The terminal automatically activates the AI ​​model and notifies the network-side device.

[0366] The terminal instructs the network-side device to set a timer or time period for deactivating the AI ​​model. During the specified timer's runtime or the specified time period, the terminal is unable to perform interference prediction or report predicted interference information. In one case, candidate values ​​for the timer's duration or the time period include {20ms, 50ms, 100ms, 200ms, 1000ms, 2000ms, ...}, or other candidate values, which are not limited here.

[0367] Behavior 2: Model retraining.

[0368] The terminal instructs the network-side device to provide a timer or time period. During the indicated timer's runtime or within the indicated time period, the terminal expects the network-side device to continue sending reference signals for interference measurement, but the terminal cannot or does not expect to report interference prediction information. During the indicated timer's runtime or within the indicated time period, the terminal can measure the interference measurement reference signals sent by the network-side device, collect data, and retrain the model to adapt to the current network configuration or environment. In one case, after the indicated timer expires or after the indicated time period, the network-side device can continue to request the terminal to report predicted interference information. In one case, the candidate values ​​for the timer duration or time period duration include {20ms, 50ms, 100ms, 200ms, 1000ms, 2000ms, ...}, or other candidate values, which are not limited here.

[0369] In this embodiment, since interference prediction is highly correlated with the configuration and environment of neighboring cells, such as the number of UEs in neighboring cells, network load, scheduling strategy, base station beams, antenna configuration, etc., if the configuration and environment of neighboring cells change, the model may fail. By retraining the model in real time, the predictive performance of the model can be guaranteed.

[0370] In one implementation, the terminal sends an indication to the network-side device that it expects the network-side device to continue sending reference signals for interference measurement, but the terminal cannot or does not expect to report interference prediction information. For example, based on interference information over the past N time-domain units, the terminal can predict interference information over the next M² time-domain units. Figure 8 As shown, N=8, M2=4. In the case of periodic disturbance measurements, as... Figure 9 As shown, after predicting the interference information for the next four time units based on the measured values ​​of interference information over the past eight time units, the terminal instructs the network-side device to set a timer or time period. During the specified timer's runtime or the specified time period, the terminal expects the network-side device to continue sending reference signals for interference measurement, but the terminal cannot or does not expect to report interference prediction information. Optionally, during the specified timer's runtime or the specified time period, the terminal can measure the interference measurement reference signals sent by the network-side device and collect data to retrain the model.

[0371] In one implementation, the reference signal used for interference measurement is the same as the reference signal associated in the CSI reporting configuration of the predicted interference information reported by the terminal; or the terminal requests the configuration of reference signal resources for interference measurement from the network-side device; or the configuration of reference signal resources for interference measurement is the same as the configuration of reference signal resources associated with model inference.

[0372] Behavior 3: Request a model update.

[0373] The terminal sends a model update request to the network-side device. The request contains at least one model identifier or version number and is used to request the network-side device to update the model's structure or parameters.

[0374] In this embodiment, by deactivating the AI ​​model, the probability of the terminal reporting inaccurate interference prediction results to the network-side device is reduced. This increases the likelihood that the network-side device will configure or schedule communication resources for the terminal based on the most accurate interference prediction results, thereby ensuring the terminal's communication performance. Furthermore, by retraining the AI ​​model in real time, the predictive performance of the AI ​​model can be guaranteed even if the configuration of neighboring cells and the environment change.

[0375] In some embodiments, the method 300 further includes:

[0376] The terminal reports its capability information.

[0377] The capability information is used to instruct the terminal to determine or report the capability of the first information.

[0378] For example, when the terminal reports the capability information, the network-side device, after receiving the capability information, can configure configuration information for determining the first information to the terminal based on the capability information.

[0379] In this embodiment, since the capability information can assist the network-side device in configuring configuration information for the terminal to determine or report the first information, and / or can assist the network-side device in configuring configuration information for determining or reporting interference information predicted by the terminal, the terminal reporting the capability information can improve the configuration efficiency of the network-side device in configuring information to the terminal.

[0380] In some embodiments, the capability information includes at least one of the following:

[0381] 1. Caching capability indication information, used to indicate the terminal's ability to cache interference information.

[0382] In this embodiment, considering that receivers often need to cache interference measurement information and interference prediction information for a period of time for comparison, but different terminals have different and limited cache spaces, the terminal reports its cache capacity to the network-side device. This can assist the network-side device in configuring configuration information for the terminal to determine or report the first information, and / or assist the network-side device in configuring configuration information for determining or reporting the interference information predicted by the terminal, thereby improving the configuration efficiency of the network-side device in configuring information to the terminal.

[0383] In some embodiments, the indication information of the caching capability includes at least one of the following: the duration of the terminal caching interference information, the number of instances of the terminal caching interference information, the number of interference measurement instances of the terminal caching interference information, and the number of interference prediction instances of the terminal caching interference information.

[0384] For example, the duration for which the terminal caches interference information includes at least one of the following: the time interval between the terminal receiving an indication from the network-side device to trigger the terminal to determine or report the first information and reporting the first information; or the time interval between the terminal receiving the indication from the network-side device to trigger the terminal to determine or report the first information and determining the first information. For example, the time length could be 20ms, 50ms, or 100ms, etc.

[0385] For example, the number of instances of the interference information includes at least one of the following: the number of instances from the time the terminal receives the indication information sent by the network-side device to trigger the terminal to determine or report the first information, to the time the terminal reports the first information; or the number of instances from the time the terminal receives the indication information sent by the network-side device to trigger the terminal to determine or report the first information, to the time the first information is determined. The number of instances of the interference information may include at least one of the following: the number of interference measurement instances of the interference information, and the number of interference prediction instances of the interference information. For example, the number of instances of the interference information may be 10, 20, or 50, etc.

[0386] For example, the number of interference measurement instances / number of interference prediction instances includes: the number of interference measurement instances / number of interference prediction instances included between the terminal receiving the instruction information sent by the network-side device to trigger the terminal to determine or report the first information and reporting the first information; and the number of interference measurement instances / number of interference prediction instances included between the terminal receiving the instruction information sent by the network-side device to trigger the terminal to determine or report the first information and determining the first information. The number of interference measurement instances / number of interference prediction instances can be 10, 20, or 50, etc.

[0387] In this embodiment, by refining the indication information of the caching capability, the terminal can report appropriate information according to its own capabilities. This not only enables the reporting of the indication information of the caching capability, but also improves the flexibility of the reporting of the indication information of the caching capability.

[0388] 2. The terminal determines or reports the frequency of the first information.

[0389] For example, the frequency at which the terminal determines or reports the first information refers to the minimum time interval between two consecutive reports of the first information.

[0390] In this embodiment, since different terminals may have different capabilities, the frequency at which the terminal determines or reports the first information may vary. For example, some terminals may support reporting once every 10 seconds, while others may support reporting once every 1 second. The frequency at which the terminal reports the first information to the network-side device can assist the network-side device in configuring configuration information for the terminal to determine or report the first information, and / or can assist the network-side device in configuring configuration information for determining or reporting interference information predicted by the terminal, thereby improving the configuration efficiency of the network-side device in configuring information to the terminal.

[0391] 3. Information for indicating a first time interval, the first time interval including at least one of the following: the time interval from when the terminal receives the instruction information for indicating a first operation to when the first operation is completed; the time interval from when the terminal sends the instruction information for indicating a first operation to when the first operation is completed; the time interval from when the terminal starts executing the first operation to when the first operation is completed; a second time interval from when the terminal deactivates a first model to when it activates a second model; wherein the first operation includes at least one of the following: deactivating the AI ​​model, activating the AI ​​model, switching the AI ​​model; the first model or the second model is the AI ​​model, the second time interval includes the operation time for activating the second model, or the second time interval includes the operation time for deactivating the first model and the operation time for activating the second model.

[0392] For example, when the first model is the AI ​​model, the second time interval is the time interval between the terminal deactivating the AI ​​model and activating other models; when the second model is the AI ​​model, the second time interval is the time interval between the terminal deactivating the model that the terminal is currently running and activating the AI ​​model.

[0393] For example, the network-side device can also determine the second time interval based on the parameters reported by the terminal.

[0394] For example, the terminal does not predict interference information during the first time interval. For instance, it can be assumed that the terminal cannot perform model inference operations during the first time interval; in other words, the terminal cannot predict interference information during the first time interval.

[0395] For example, the first time interval is: the time interval from when the terminal receives the instruction information to activate / deactivate the AI ​​model, the instruction information to switch the AI ​​model, to when the specified operation is completed; or the time interval from when the terminal reports or the network-side device receives the notification information to activate / deactivate the AI ​​model, the notification information to switch the AI ​​model, to when the terminal completes the specified operation; or the time interval from when the terminal starts activating / deactivating the AI ​​model, switching the AI ​​model, to when the specified operation is completed.

[0396] In this embodiment, since the terminal may need a certain time delay to perform operations such as model activation / deactivation and switching, the terminal reports this time delay to the network-side device. Specifically, the terminal reports information indicating the first time interval to the network-side device. This assists the network-side device in configuring configuration information for the terminal to determine or report the first information, and / or in configuring configuration information for determining or reporting interference information predicted by the terminal, thereby improving the configuration efficiency of the network-side device in providing configuration information to the terminal. Furthermore, the terminal's reporting of information indicating the first time interval to the network-side device assists the network-side device in making activation / deactivation and switching decisions for the model running on the terminal, thereby improving model management efficiency.

[0397] In some embodiments, the first time interval is determined according to at least one of the following:

[0398] Capability level, used to indicate the level of capabilities supported by the terminal;

[0399] The maximum number of computing units in AI computing;

[0400] The number of available computing units for AI computing;

[0401] The maximum number of threads for AI computation;

[0402] The number of available threads for AI computation;

[0403] Thread load of available threads for AI computing;

[0404] The complexity or complexity level of the AI ​​model;

[0405] The operation time to activate the AI ​​model;

[0406] The operation time to activate the AI ​​model;

[0407] The complexity or complexity level of the AI ​​model is determined based on at least one of the following: the number of parameters of the AI ​​model, the input dimension of the AI ​​model, and the output dimension of the AI ​​model.

[0408] For example, different ability levels correspond to different first time intervals, or different ability levels correspond to different time interval ranges.

[0409] For example, a thread may include multiple computing units, which may correspond one-to-one with actual physical computing units, or they may be logical computing units. The specific mapping method between physical computing units depends on the terminal implementation. The computing units of different threads are independent; the number of computing units in different threads may be the same or different, which is not limited here. Figure 13 As shown, the unavailable computing units may be occupied by other tasks or reserved computing units.

[0410] For example, the AI ​​computation may also be referred to as AI processing.

[0411] For example, the maximum number of threads for the AI ​​computation is 1 or other values.

[0412] For example, the complexity or level of the AI ​​model may include at least one of the following: the complexity or level of the AI ​​model as a model to be deactivated, and the complexity or level of the AI ​​model as a model to be activated.

[0413] For example, the number of parameters of the AI ​​model is related to at least one of the number of parameters, the number of layers, and the number of modules.

[0414] For example, the first time interval or the second time interval includes the operation time for activating the AI ​​model.

[0415] For example, the first time interval or the second time interval may or may not include the operation time for deactivating the AI ​​model.

[0416] In one implementation, the time overhead of the terminal deactivating the AI ​​model can be ignored. The main focus is on the complexity of activating the AI ​​model. That is, the higher the complexity or level of the AI ​​model as the model to be activated, the larger the first time interval or the second time interval. For example, the first time interval or the second time interval includes the operation time for deactivating the AI ​​model.

[0417] In one implementation, the time overhead of the terminal deactivating the AI ​​model is not negligible, and the first time interval or the second time interval does not include the time of the terminal deactivating the AI ​​model.

[0418] For example, the network-side device can also determine the operation time to activate the AI ​​model based on the parameters reported by the terminal.

[0419] In this embodiment, the first time interval is determined by the terminal's capability level, AI calculation-related information, and deactivation / activation-related information, so that the first time interval reported by the terminal can reflect the delay of the terminal reporting the first information to the network-side device, thereby improving the accuracy of the first time interval.

[0420] In some embodiments, the first time interval satisfies at least one of the following:

[0421] The first time interval is positively correlated with the complexity or complexity level;

[0422] The first time interval is negatively correlated with the number of available computing units or the number of available threads;

[0423] The first time interval is positively correlated with the thread load.

[0424] For example, when the first time interval is positively correlated with the complexity, the relationship between the first time interval and the complexity is shown in the following formula:

[0425] T = α × (relevant terms of complexity / relevant terms of the number of available computational units) + X.

[0426] Here, α depends on the UE's capabilities or network policies; X represents other potentially relevant terms, which are not limited here.

[0427] For example, when the time interval is positively correlated with the thread load, the relationship between the time interval and the thread load is shown in the following formula:

[0428] T = α × β × complexity related terms + X.

[0429] Here, α depends on the UE capability or network policy, β is the thread load, and X is other possible related terms, which are not limited here.

[0430] In this embodiment, when the first time interval is positively correlated with the complexity or complexity level, negatively correlated with the number of available computing units or the number of available threads, or positively correlated with the thread load, the first time interval reported by the terminal can reflect the delay in the terminal reporting the first information to the network-side device, thereby improving the accuracy of the first time interval.

[0431] The wireless communication method provided in this application can be executed by a wireless communication device. This application uses an example of a wireless communication device executing a wireless communication method to illustrate the wireless communication device provided in this application.

[0432] This application provides a wireless communication device. As an example, the wireless communication device may be a communication equipment or a component within a communication equipment, such as a chip. The communication equipment may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed above, and the network-side device may include, but is not limited to, the type of network-side device 12 listed above. This application does not impose specific limitations.

[0433] The wireless communication device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, etc., such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0434] For details, see Figure 14 When the wireless communication device is a terminal or a component within a terminal, the wireless communication device 400 includes:

[0435] The sending module 401 is used to report the first information;

[0436] Wherein, the first information is used to indicate at least one of the following:

[0437] The prediction accuracy for T1 interference information is T1≥1;

[0438] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0439] Performance information of artificial intelligence (AI) models.

[0440] In some embodiments, the first information includes at least one of the following:

[0441] The first indication information is used to indicate the prediction accuracy of the first interference information among the T1 interference information;

[0442] The second indication information is used to indicate the prediction accuracy of the interference information in the first time domain unit among the T2 time domain units;

[0443] The third indication information is used to indicate at least one of the following: the prediction accuracy of T3 interference information, the prediction accuracy of interference information within T4 time-domain units, and whether the AI ​​model has failed, where T3≥1 and T4≥1.

[0444] In some embodiments, the first indication information is used to indicate at least one of the following:

[0445] The difference between the predicted value and the measured value of the first interference information;

[0446] Is the predicted value of the first interference information accurate?

[0447] In some embodiments, the second indication information is used to indicate at least one of the following:

[0448] The average value of the first difference corresponding to the first time domain unit;

[0449] The average of the absolute values ​​of the first differences corresponding to the first time-domain unit;

[0450] The number of accurately predicted instances corresponding to the first time-domain unit;

[0451] The ratio of the number of accurately predicted instances corresponding to the first time domain unit to the total number of predicted instances corresponding to the first time domain unit;

[0452] The number of instances where the prediction is inaccurate corresponding to the first time-domain unit;

[0453] The ratio of the number of inaccurate predictions corresponding to the first time domain unit to the total number of predictions corresponding to the first time domain unit;

[0454] Whether the prediction instance corresponding to the first time domain unit is accurate;

[0455] Wherein, the first difference is the difference between the predicted value and the measured value of the interference information within the first time domain unit.

[0456] In some embodiments, the third indication information is used to indicate at least one of the following:

[0457] The average, weighted average, maximum, or minimum value of the second difference;

[0458] The average, weighted average, maximum, or minimum of the third difference;

[0459] Wherein, the second difference is the difference between the predicted value and the measured value of the interference information in the T3 interference information, and the third difference is based on the difference between the predicted value and the measured value of the interference information in the time domain unit in the T4 time domain units.

[0460] In some embodiments, the device 400 further includes a first processing module, which, before the sending module 401 reports the first information, is configured to:

[0461] Based on interference information within N time-domain units, or predicting M1 interference information and M2 interference information within M2 time-domain units, where N≥1, M1≥T1, and M2≥T2.

[0462] In some embodiments, the T1 interference information includes one of the following: the first T1 interference information in the M1 interference information, the T1 interference information indicated by the network-side device in the M1 interference information, the T1 interference information determined by the terminal in the M1 interference information, and T1 interference information at equal intervals in the M1 interference information, where M1 > T1; or

[0463] The T2 time domain units include one of the following: the first T2 time domain units in the M2 time domain units, the T2 time domain units indicated by the network-side device in the M2 time domain units, the T2 time domain units determined by the terminal in the M2 time domain units, and the T2 time domain units that are equally spaced in the M2 time domain units, where M2 > T2.

[0464] In some embodiments, the device 400 further includes a first receiving module, which, before the sending module 401 reports the first information, is configured to:

[0465] The terminal receives at least one first reporting configuration information, which is used by the terminal to determine or report interference information predicted by the terminal.

[0466] In some embodiments, the first reporting configuration information is further used by the terminal to determine or report the first information.

[0467] In some embodiments, the device 400 further includes a second receiving module, which is used before the sending module 401 reports the first information to:

[0468] The terminal receives second reporting configuration information, which is associated with at least one first reporting configuration information. The second reporting configuration information is used by the terminal to determine or report the first information, and the first reporting configuration information is used by the terminal to determine or report the interference information predicted by the terminal.

[0469] In some embodiments, the second reported configuration information is associated with at least one first reported configuration information, including at least one of the following:

[0470] The second reported configuration information is the identification information of the reference signal resource configuration that is associated with the first reported configuration information;

[0471] The second reported configuration information is associated with the same reference resource identifier information as the first reported configuration information;

[0472] The second reported configuration information includes the identification information of the first reported configuration information.

[0473] In some embodiments, the second reporting configuration information is used to configure the reporting period of the first information.

[0474] In some embodiments, the first reporting configuration information is used to configure the reporting period of the interference information predicted by the terminal.

[0475] In some embodiments, the sending module 401 is specifically used for:

[0476] The first piece of information is reported periodically;

[0477] The reporting period for the first information satisfies one of the following:

[0478] The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal.

[0479] The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI).

[0480] The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal;

[0481] The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal.

[0482] The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal.

[0483] In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

[0484] In some embodiments, the first offset value includes one or more reporting periods of the interference information predicted by the terminal; or

[0485] The first offset value includes one or more reporting periods of the first information; or

[0486] At least one of the first offset value, the maximum value of the first offset value, and the minimum value of the first offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0487] In some embodiments, the second offset value is determined based on at least one of the following: the reporting period of the first information, the SFN of the system frame used to report the first information, the number of time-domain units included in the SFN used to report the first information, and the index of the time-domain unit used to report the first information; or

[0488] At least one of the second offset value, the maximum value of the second offset value, and the minimum value of the second offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0489] In some embodiments, the first information and the interference information predicted by the terminal are reported via a Channel State Information (CSI) feedback report; or

[0490] The first information is reported via Media Access Control (MAC) layer signaling or Radio Resource Control (RRC) signaling, and the interference information predicted by the terminal is reported via Channel State Information (CSI) feedback report; or

[0491] The first information is sent via deactivation request information or deactivation notification information. The deactivation request information is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period. The deactivation notification information is used to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model is unavailable within a target time period.

[0492] In some embodiments, the sending module 401 is specifically used for:

[0493] If the first condition is met, report the first piece of information;

[0494] The first condition includes at least one of the following:

[0495] The terminal receives information to trigger the terminal to report the first information;

[0496] The prediction accuracy of the T1 interference information meets the reporting trigger condition;

[0497] The prediction accuracy of the interference information within the T2 time-domain units meets the reporting triggering condition;

[0498] The performance information meets the reporting trigger conditions;

[0499] The serving cell of the terminal has changed;

[0500] The bandwidth portion of the terminal's BWP or the activated BWP changes.

[0501] In some embodiments, the first information is associated with at least one of the following: a first transmission configuration indication TCI state, the receiving beam of the terminal, and the receiving port of the terminal;

[0502] The first TCI state or the received beam is determined based on at least one of the following: a transmission configuration indication TCI state associated with a reference signal used for interference measurement, or a transmission configuration indication TCI state activated by a media access control element MAC CE.

[0503] In some embodiments, the first information includes at least one of the following:

[0504] The TCI status associated with the first information;

[0505] The TCI state associated with each of the T1 interference messages;

[0506] The Transmission Configuration Indicator (TCI) status associated with each of the T2 time-domain units;

[0507] The transmission configuration associated with the AI ​​model indicates the TCI status;

[0508] The receiving beam or receiving port associated with the first information;

[0509] The receiving beam or receiving port associated with each of the T1 interference information;

[0510] The receiving beam or receiving port associated with each of the T2 time-domain units;

[0511] The AI ​​model is associated with a receiving beam or receiving port.

[0512] In some embodiments, the apparatus further includes a third receiving module or a second processing module, or the transmitting module 401 is further configured to perform at least one of the following:

[0513] Send a deactivation request message to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period;

[0514] Send a deactivation notification message to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model will be unavailable within a target time period.

[0515] Send an update request message to request an update to the AI ​​model;

[0516] The third receiving module is used to receive deactivation instruction information, which is used to instruct the terminal to deactivate the AI ​​model, or to instruct the terminal to deactivate the AI ​​model within a target time period.

[0517] The second processing module is used to perform at least one of the following:

[0518] Deactivate the AI ​​model;

[0519] During the target time period for deactivating the AI ​​model, the AI ​​model is retrained.

[0520] In some embodiments, the sending module 401 is further configured to:

[0521] Report the capability information of the terminal;

[0522] The capability information is used to instruct the terminal to determine or report the capability of the first information.

[0523] In some embodiments, the capability information includes at least one of the following:

[0524] Caching capability indication information, used to indicate the terminal's ability to cache interference information;

[0525] The terminal determines or reports the frequency of the first information;

[0526] Information used to indicate a first time interval, the first time interval including at least one of the following: the time interval from when the terminal receives the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal sends the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal starts to execute the first operation to when the first operation is completed; and the second time interval from when the terminal deactivates the first model to when the second model is activated.

[0527] The first operation includes at least one of the following: deactivating the AI ​​model, activating the AI ​​model, or switching the AI ​​model;

[0528] The first model or the second model is the AI ​​model, and the second time interval includes the operation time for activating the second model, or the second time interval includes the operation time for deactivating the first model and the operation time for activating the second model.

[0529] In some embodiments, the indication information of the caching capability includes at least one of the following: the duration of the terminal caching interference information, the number of instances of the terminal caching interference information, the number of interference measurement instances of the terminal caching interference information, and the number of interference prediction instances of the terminal caching interference information.

[0530] In some embodiments, the first time interval is determined according to at least one of the following:

[0531] Capability level, used to indicate the level of capabilities supported by the terminal;

[0532] The maximum number of computing units in AI computing;

[0533] The number of available computing units for AI computing;

[0534] The maximum number of threads for AI computation;

[0535] The number of available threads for AI computation;

[0536] Thread load of available threads for AI computing;

[0537] The complexity or complexity level of the AI ​​model;

[0538] The operation time to activate the AI ​​model;

[0539] The operation time to activate the AI ​​model;

[0540] The complexity or complexity level of the AI ​​model is determined based on at least one of the following: the number of parameters of the AI ​​model, the input dimension of the AI ​​model, and the output dimension of the AI ​​model.

[0541] In some embodiments, the first time interval satisfies at least one of the following:

[0542] The first time interval is positively correlated with the complexity or complexity level;

[0543] The first time interval is negatively correlated with the number of available computing units or the number of available threads;

[0544] The first time interval is positively correlated with the thread load.

[0545] See Figure 15 When the wireless communication device is a network-side device or a component within a network-side device, the wireless communication device 500 includes:

[0546] Receiver module 501 is used to receive the first information;

[0547] Wherein, the first information is used to indicate at least one of the following:

[0548] The prediction accuracy for T1 interference information is T1≥1;

[0549] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0550] Performance information of artificial intelligence (AI) models.

[0551] In some embodiments, the first information includes at least one of the following:

[0552] The first indication information is used to indicate the prediction accuracy of the first interference information among the T1 interference information;

[0553] The second indication information is used to indicate the prediction accuracy of the interference information in the first time domain unit among the T2 time domain units;

[0554] The third indication information is used to indicate at least one of the following: the prediction accuracy of T3 interference information, the prediction accuracy of interference information within T4 time-domain units, and whether the AI ​​model has failed, where T3≥1 and T4≥1.

[0555] In some embodiments, the first indication information is used to indicate at least one of the following:

[0556] The difference between the predicted value and the measured value of the first interference information;

[0557] Is the predicted value of the first interference information accurate?

[0558] In some embodiments, the second indication information is used to indicate at least one of the following:

[0559] The average value of the first difference corresponding to the first time domain unit;

[0560] The average of the absolute values ​​of the first differences corresponding to the first time-domain unit;

[0561] The number of accurately predicted instances corresponding to the first time-domain unit;

[0562] The ratio of the number of accurately predicted instances corresponding to the first time domain unit to the total number of predicted instances corresponding to the first time domain unit;

[0563] The number of instances where the prediction is inaccurate corresponding to the first time-domain unit;

[0564] The ratio of the number of inaccurate predictions corresponding to the first time domain unit to the total number of predictions corresponding to the first time domain unit;

[0565] Whether the prediction instance corresponding to the first time domain unit is accurate;

[0566] Wherein, the first difference is the difference between the predicted value and the measured value of the interference information within the first time domain unit.

[0567] In some embodiments, the third indication information is used to indicate at least one of the following:

[0568] The average, weighted average, maximum, or minimum value of the second difference;

[0569] The average, weighted average, maximum, or minimum of the third difference;

[0570] Wherein, the second difference is the difference between the predicted value and the measured value of the interference information in the T3 interference information, and the third difference is based on the difference between the predicted value and the measured value of the interference information in the time domain unit in the T4 time domain units.

[0571] In some embodiments, the apparatus further includes a first transmitting module, which, before the receiving module 501 receives the first information, is configured to:

[0572] Send at least one first reporting configuration information, which is used by the terminal to determine or report the interference information predicted by the terminal.

[0573] In some embodiments, the first reporting configuration information is further used by the terminal to determine or report the first information.

[0574] In some embodiments, the apparatus further includes a second transmitting module, wherein before the receiving module 501 receives the first information, the second transmitting module is configured to:

[0575] Send a second reporting configuration information, which is associated with at least one first reporting configuration information. The second reporting configuration information is used by the terminal to determine or report the first information, and the first reporting configuration information is used by the terminal to determine or report the interference information predicted by the terminal.

[0576] In some embodiments, the second reported configuration information is associated with at least one first reported configuration information, including at least one of the following:

[0577] The second reported configuration information is the identification information of the reference signal resource configuration that is associated with the first reported configuration information;

[0578] The second reported configuration information is associated with the same reference resource identifier information as the first reported configuration information;

[0579] The second reported configuration information includes the identification information of the first reported configuration information.

[0580] In some embodiments, the second reporting configuration information is used to configure the reporting period of the first information.

[0581] In some embodiments, the first reporting configuration information is used to configure the reporting period of the interference information predicted by the terminal.

[0582] In some embodiments, the receiving module 501 is specifically used for:

[0583] The first information is received periodically;

[0584] The reporting period for the first information satisfies one of the following:

[0585] The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal.

[0586] The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI).

[0587] The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal.

[0588] The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal.

[0589] The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal.

[0590] In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

[0591] In some embodiments, the first offset value includes one or more reporting periods of interference information predicted by the terminal; or

[0592] The first offset value includes one or more reporting periods of the first information; or

[0593] At least one of the first offset value, the maximum value of the first offset value, and the minimum value of the first offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0594] In some embodiments, the second offset value is determined based on at least one of the following: the reporting period of the first information, the SFN of the system frame used to report the first information, the number of time-domain units included in the SFN used to report the first information, and the index of the time-domain unit used to report the first information; or

[0595] At least one of the second offset value, the maximum value of the second offset value, and the minimum value of the second offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

[0596] In some embodiments, the first information and the interference information predicted by the terminal are received via a Channel State Information (CSI) feedback report; or

[0597] The first information is received via Media Access Control (MAC) layer signaling or Radio Resource Control (RRC) signaling, and the interference information predicted by the terminal is received via Channel State Information (CSI) feedback report; or

[0598] The first information is sent via deactivation request information or deactivation notification information. The deactivation request information is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period. The deactivation notification information is used to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model is unavailable within a target time period.

[0599] In some embodiments, the apparatus further includes a third transmitting module, which, before the receiving module 501 receives the first information, is configured to:

[0600] Send information to trigger the terminal to report the first information.

[0601] In some embodiments, the first information is associated with at least one of the following: a first transmission configuration indication TCI state, the terminal's receive beam, and the terminal's receive port;

[0602] The first TCI state or the received beam is determined based on at least one of the following: a transmission configuration indication TCI state associated with a reference signal used for interference measurement, or a transmission configuration indication TCI state activated by a media access control element MAC CE.

[0603] In some embodiments, the first information includes at least one of the following:

[0604] The TCI status associated with the first information;

[0605] The TCI state associated with each of the T1 interference messages;

[0606] The Transmission Configuration Indicator (TCI) status associated with each of the T2 time-domain units;

[0607] The transmission configuration associated with the AI ​​model indicates the TCI status;

[0608] The receiving beam or receiving port associated with the first information;

[0609] The receiving beam or receiving port associated with each of the T1 interference information;

[0610] The receiving beam or receiving port associated with each of the T2 time-domain units;

[0611] The AI ​​model is associated with a receiving beam or receiving port.

[0612] In some embodiments, the method apparatus further includes a first processing module or a fourth transmitting module, or the receiving module 501 is further configured to perform at least one of the following:

[0613] Receive deactivation request information, which is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period;

[0614] Receive deactivation notification information to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model will be unavailable within a target time period.

[0615] Receive update request information to request an update to the AI ​​model;

[0616] The fourth sending module is used to send deactivation instruction information to instruct the terminal to deactivate the AI ​​model, or to instruct the terminal to deactivate the AI ​​model within a target time period.

[0617] The first processing module is used to deactivate the AI ​​model.

[0618] In some embodiments, the receiving module 501 is further configured to:

[0619] Receive terminal capability information;

[0620] The capability information is used to instruct the terminal to determine or report the capability of the first information.

[0621] In some embodiments, the capability information includes at least one of the following:

[0622] Caching capability indication information, used to indicate the terminal's ability to cache interference information;

[0623] The terminal determines or reports the frequency of the first information;

[0624] Information used to indicate a first time interval, the first time interval including at least one of the following: the time interval from when the terminal receives the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal sends the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal starts to execute the first operation to when the first operation is completed; and the second time interval from when the terminal deactivates the first model to when the second model is activated.

[0625] The first operation includes at least one of the following: deactivating the AI ​​model, activating the AI ​​model, or switching the AI ​​model;

[0626] The first model or the second model is the AI ​​model, and the second time interval includes the operation time for activating the second model, or the second time interval includes the operation time for deactivating the first model and the operation time for activating the second model.

[0627] In some embodiments, the indication information of the caching capability includes at least one of the following: the duration of the terminal caching interference information, the number of instances of the terminal caching interference information, the number of interference measurement instances of the terminal caching interference information, and the number of interference prediction instances of the terminal caching interference information.

[0628] In some embodiments, the first time interval is determined according to at least one of the following:

[0629] Capability level, used to indicate the level of capabilities supported by the terminal;

[0630] The maximum number of computing units in AI computing;

[0631] The number of available computing units for AI computing;

[0632] The maximum number of threads for AI computation;

[0633] The number of available threads for AI computation;

[0634] Thread load of available threads for AI computing;

[0635] The complexity or complexity level of the AI ​​model;

[0636] The operation time to activate the AI ​​model;

[0637] The operation time to activate the AI ​​model;

[0638] The complexity or complexity level of the AI ​​model is determined based on at least one of the following: the number of parameters of the AI ​​model, the input dimension of the AI ​​model, and the output dimension of the AI ​​model.

[0639] In some embodiments, the first time interval satisfies at least one of the following:

[0640] The first time interval is positively correlated with the complexity or complexity level;

[0641] The first time interval is negatively correlated with the number of available computing units or the number of available threads;

[0642] The first time interval is positively correlated with the thread load.

[0643] The apparatus provided in this application embodiment can achieve... Figure 7 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[0644] like Figure 16 As shown in the illustration, this application also provides a communication device 600, including a processor 601 and a memory 602. The memory 602 stores programs or instructions that can run on the processor 601. For example, when the communication device 600 is a terminal, the program or instructions executed by the processor 601 implement the various steps of the above-described wireless communication method embodiments and achieve the same technical effect. When the communication device 600 is a network-side device, the program or instructions executed by the processor 601 implement the various steps of the above-described wireless communication method embodiments and achieve the same technical effect. To avoid repetition, further details are omitted here.

[0645] This application embodiment also provides a terminal, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 7 The steps in the method embodiment shown are illustrated. This terminal embodiment corresponds to the above-described terminal-side method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this terminal embodiment and achieve the same technical effect. The terminal can be... Figure 14 The wireless communication device shown. Specifically, Figure 17 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[0646] The terminal 700 includes, but is not limited to, at least some of the following components: radio frequency unit 701, network module 702, audio output unit 703, input unit 704, sensor 705, display unit 706, user input unit 707, interface unit 708, memory 709, and processor 710.

[0647] Those skilled in the art will understand that the terminal 700 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 710 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 17 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[0648] It should be understood that, in this embodiment, the input unit 704 may include a graphics processor 7041 and a microphone 7042. The graphics processor 7041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 706 may include a display panel 7061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[0649] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 701 can transmit it to the processor 710 for processing; in addition, the radio frequency unit 701 can send uplink data to the network-side device. Typically, the radio frequency unit 701 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[0650] The memory 709 can be used to store software programs or instructions, as well as various data. The memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 709 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 709 in the embodiments of this application includes, but is not limited to, these and any other suitable types of memory.

[0651] Processor 710 may include one or more processing units; optionally, processor 710 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into processor 710.

[0652] Among them, the radio frequency unit 701 is used to report the first information;

[0653] Wherein, the first information is used to indicate at least one of the following:

[0654] The prediction accuracy for T1 interference information is T1≥1;

[0655] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0656] Performance information of artificial intelligence (AI) models.

[0657] In this embodiment, the terminal reports first information used to determine the accuracy of predictions or the performance information of AI models, enabling the network-side device to configure or schedule appropriate communication resources for the terminal based on the first information, thereby ensuring the communication performance of the terminal.

[0658] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of method embodiment 300 and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[0659] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement, for example... Figure 7 The steps of the method embodiment shown are illustrated. This network-side device embodiment corresponds to the above-described network-side device method embodiment. All implementation processes and methods of the above-described method embodiments can be applied to this network-side device embodiment and can achieve the same technical effect.

[0660] Specifically, embodiments of this application also provide a network-side device, which can be... Figure 15 The wireless communication device shown. (As shown) Figure 18 As shown, the network-side device 800 includes: an antenna 81, a radio frequency (RF) device 82, a baseband device 83, a processor 84, and a memory 85. The antenna 81 is connected to the RF device 82. In the uplink direction, the RF device 82 receives information through the antenna 81 and transmits the received information to the baseband device 83 for processing. In the downlink direction, the baseband device 83 processes the information to be transmitted and sends it to the RF device 82. The RF device 82 processes the received information and transmits it through the antenna 81.

[0661] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 83, which includes a baseband processor.

[0662] Baseband device 83 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 18 As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 85 via a bus interface to call the program or instructions in the memory 85 to execute the network-side device operations shown in the above method embodiment.

[0663] The network-side device may also include a network interface 86, such as a Common Public Radio Interface (CPRI).

[0664] Among them, the radio frequency device 82 is used to receive the first information;

[0665] Wherein, the first information is used to indicate at least one of the following:

[0666] The prediction accuracy for T1 interference information is T1≥1;

[0667] The prediction accuracy of interference information within T2 time-domain units is T2≥1;

[0668] Performance information of artificial intelligence (AI) models.

[0669] Furthermore, the network-side device 800 in this embodiment of the application also includes: a program or instructions stored in a memory 85 and executable on a processor 84, wherein the processor 84 calls the program or instructions in the memory 85 to execute. Figure 15 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[0670] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described wireless communication method embodiments and achieve the same technical effects. To avoid repetition, they will not be described again here.

[0671] The processor mentioned above is either the processor in the terminal described in the above embodiments or the processor in the network-side device. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[0672] This application embodiment also provides a chip, which 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-described wireless communication method embodiments and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0673] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0674] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described wireless communication method embodiments, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0675] This application also provides a wireless communication system, including: a terminal and a network-side device, wherein the terminal can be used to execute the steps of the wireless communication method described above, and the network-side device can be used to execute the steps of the wireless communication method described above.

[0676] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0677] From the above description of the 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 necessary general-purpose hardware platforms, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.), and the computer software product includes several instructions to cause the terminal or network-side device to execute the methods described in the various embodiments of this application.

[0678] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other implementations under the guidance of this application without departing from the spirit and scope of the claims. All of these implementations are within the protection scope of this application.

Claims

1. A wireless communication method, characterized in that, include: The terminal reports the first piece of information; Wherein, the first information is used to indicate at least one of the following: The prediction accuracy for T1 interference information is T1≥1; The prediction accuracy of interference information within T2 time-domain units is T2≥1; Performance information of artificial intelligence (AI) models.

2. The method according to claim 1, characterized in that, The first information includes at least one of the following: The first indication information is used to indicate the prediction accuracy of the first interference information among the T1 interference information; The second indication information is used to indicate the prediction accuracy of the interference information in the first time domain unit among the T2 time domain units; The third indication information is used to indicate at least one of the following: the prediction accuracy of T3 interference information, the prediction accuracy of interference information within T4 time-domain units, and whether the AI ​​model has failed, where T3≥1 and T4≥1.

3. The method according to claim 2, characterized in that, The first indication information is used to indicate at least one of the following: The difference between the predicted value and the measured value of the first interference information; Is the predicted value of the first interference information accurate? 4. The method according to claim 2 or 3, characterized in that, The second indication information is used to indicate at least one of the following: The average value of the first difference corresponding to the first time domain unit; The average of the absolute values ​​of the first differences corresponding to the first time-domain unit; The number of accurately predicted instances corresponding to the first time-domain unit; The ratio of the number of accurately predicted instances corresponding to the first time domain unit to the total number of predicted instances corresponding to the first time domain unit; The number of instances where the prediction is inaccurate corresponding to the first time-domain unit; The ratio of the number of inaccurate predictions corresponding to the first time domain unit to the total number of predictions corresponding to the first time domain unit; Whether the prediction instance corresponding to the first time domain unit is accurate; Wherein, the first difference is the difference between the predicted value and the measured value of the interference information within the first time domain unit.

5. The method according to any one of claims 2 to 4, characterized in that, The third indication information is used to indicate at least one of the following: The average, weighted average, maximum, or minimum value of the second difference; The average, weighted average, maximum, or minimum of the third difference; Wherein, the second difference is the difference between the predicted value and the measured value of the interference information in the T3 interference information, and the third difference is based on the difference between the predicted value and the measured value of the interference information in the time domain unit in the T4 time domain units.

6. The method according to any one of claims 1 to 5, characterized in that, Before the terminal reports the first information, the method further includes: The terminal predicts interference information based on N time-domain units, or predicts interference information in M1 time-domain units, where N≥1, M1≥T1, and M2≥T2.

7. The method according to claim 6, characterized in that, The T1 interference information includes one of the following: the first T1 interference information among the M1 interference information, the T1 interference information indicated by the network-side device among the M1 interference information, the T1 interference information determined by the terminal among the M1 interference information, or T1 interference information at equal intervals among the M1 interference information, where M1 > T1; or The T2 time domain units include one of the following: the first T2 time domain units in the M2 time domain units, the T2 time domain units indicated by the network-side device in the M2 time domain units, the T2 time domain units determined by the terminal in the M2 time domain units, and the T2 time domain units that are equally spaced in the M2 time domain units, where M2 > T2.

8. The method according to any one of claims 1 to 7, characterized in that, Before the terminal reports the first information, the method further includes: The terminal receives at least one first reporting configuration information, which is used by the terminal to determine or report interference information predicted by the terminal.

9. The method according to claim 8, characterized in that, The first reported configuration information is also used by the terminal to determine or report the first information.

10. The method according to any one of claims 1 to 9, characterized in that, Before the terminal reports the first information, the method further includes: The terminal receives second reporting configuration information, which is associated with at least one first reporting configuration information. The second reporting configuration information is used by the terminal to determine or report the first information, and the first reporting configuration information is used by the terminal to determine or report the interference information predicted by the terminal.

11. The method according to claim 10, characterized in that, The second reported configuration information is associated with at least one first reported configuration information, including at least one of the following: The second reported configuration information is the identification information of the reference signal resource configuration that is associated with the first reported configuration information; The second reported configuration information is associated with the same reference resource identifier information as the first reported configuration information; The second reported configuration information includes the identification information of the first reported configuration information.

12. The method according to claim 10 or 11, characterized in that, The second reporting configuration information is used to configure the reporting period of the first information.

13. The method according to any one of claims 8 to 12, characterized in that, The first reporting configuration information is used to configure the reporting period of the interference information predicted by the terminal.

14. The method according to any one of claims 1 to 13, characterized in that, The terminal reports the first information, including: The terminal periodically reports the first information; The reporting period for the first information satisfies one of the following: The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal. The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI). The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal; The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal. The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal. In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

15. The method according to claim 14, characterized in that, The first offset value includes one or more reporting periods of the interference information predicted by the terminal; or The first offset value includes one or more reporting periods of the first information; or At least one of the first offset value, the maximum value of the first offset value, and the minimum value of the first offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

16. The method according to claim 14 or 15, characterized in that, The second offset value is determined based on at least one of the following: the reporting period of the first information, the SFN of the system frame used to report the first information, the number of time-domain units included in the SFN used to report the first information, and the index of the time-domain unit used to report the first information; or At least one of the second offset value, the maximum value of the second offset value, and the minimum value of the second offset value is determined by the terminal, indicated by the network-side device, or agreed upon by the protocol.

17. The method according to any one of claims 1 to 16, characterized in that, The first information and the interference information predicted by the terminal are reported through a Channel State Information (CSI) feedback report; or The first information is reported via Media Access Control (MAC) layer signaling or Radio Resource Control (RRC) signaling, and the interference information predicted by the terminal is reported via Channel State Information (CSI) feedback report; or The first information is sent via deactivation request information or deactivation notification information. The deactivation request information is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period. The deactivation notification information is used to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model is unavailable within a target time period.

18. The method according to any one of claims 1 to 17, characterized in that, The terminal reports the first information, including: If the first condition is met, the terminal reports the first information; The first condition includes at least one of the following: The terminal receives information to trigger the terminal to report the first information; The prediction accuracy of the T1 interference information meets the reporting trigger condition; The prediction accuracy of the interference information within the T2 time-domain units meets the reporting triggering condition; The performance information meets the reporting trigger conditions; The serving cell of the terminal has changed; The bandwidth portion of the terminal's BWP or the activated BWP changes.

19. The method according to any one of claims 1 to 18, characterized in that, The first information is associated with at least one of the following: the first transmission configuration indication (TCI) status, the receiving beam of the terminal, and the receiving port of the terminal; The first TCI state or the received beam is determined based on at least one of the following: a transmission configuration indication TCI state associated with a reference signal used for interference measurement, or a transmission configuration indication TCI state activated by a media access control element MAC CE.

20. The method according to any one of claims 1 to 19, characterized in that, The first information includes at least one of the following: The TCI status associated with the first information; The TCI state associated with each of the T1 interference messages; The Transmission Configuration Indicator (TCI) status associated with each of the T2 time-domain units; The transmission configuration associated with the AI ​​model indicates the TCI status; The receiving beam or receiving port associated with the first information; The receiving beam or receiving port associated with each of the T1 interference information; The receiving beam or receiving port associated with each of the T2 time-domain units; The AI ​​model is associated with a receiving beam or receiving port.

21. The method according to any one of claims 1 to 20, characterized in that, The method further includes at least one of the following: Receive deactivation instruction information, which is used to instruct the terminal to deactivate the AI ​​model, or to instruct the terminal to deactivate the AI ​​model within a target time period; Send a deactivation request message to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period; Deactivate the AI ​​model; Send a deactivation notification message to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model will be unavailable within a target time period. During the target time period for deactivating the AI ​​model, the AI ​​model is retrained. Send an update request message to request an update to the AI ​​model.

22. The method according to any one of claims 1 to 21, characterized in that, The method further includes: The terminal reports its capability information. The capability information is used to instruct the terminal to determine or report the capability of the first information.

23. The method according to claim 22, characterized in that, The capability information includes at least one of the following: Caching capability indication information, used to indicate the terminal's ability to cache interference information; The terminal determines or reports the frequency of the first information; Information used to indicate a first time interval, the first time interval including at least one of the following: the time interval from when the terminal receives the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal sends the indication information for indicating a first operation to when the first operation is completed; the time interval from when the terminal starts to execute the first operation to when the first operation is completed; and the second time interval from when the terminal deactivates the first model to when the second model is activated. The first operation includes at least one of the following: deactivating the AI ​​model, activating the AI ​​model, or switching the AI ​​model; The first model or the second model is the AI ​​model, and the second time interval includes the operation time for activating the second model, or the second time interval includes the operation time for deactivating the first model and the operation time for activating the second model.

24. The method according to claim 23, characterized in that, The indication information of the caching capability includes at least one of the following: the duration of the terminal caching interference information, the number of instances of the terminal caching interference information, the number of interference measurement instances of the terminal caching interference information, and the number of interference prediction instances of the terminal caching interference information.

25. The method according to claim 23 or 24, characterized in that, The first time interval is determined according to at least one of the following: Capability level, used to indicate the level of capabilities supported by the terminal; The maximum number of computing units in AI computing; The number of available computing units for AI computing; The maximum number of threads for AI computation; The number of available threads for AI computation; Thread load of available threads for AI computing; The complexity or complexity level of the AI ​​model; The operation time to activate the AI ​​model; The operation time to activate the AI ​​model; The complexity or complexity level of the AI ​​model is determined based on at least one of the following: the number of parameters of the AI ​​model, the input dimension of the AI ​​model, and the output dimension of the AI ​​model.

26. The method according to claim 25, characterized in that, The first time interval satisfies at least one of the following: The first time interval is positively correlated with the complexity or complexity level; The first time interval is negatively correlated with the number of available computing units or the number of available threads; The first time interval is positively correlated with the thread load.

27. A wireless communication method, characterized in that, include: The network-side device receives the first information; Wherein, the first information is used to indicate at least one of the following: The prediction accuracy for T1 interference information is T1≥1; The prediction accuracy of interference information within T2 time-domain units is T2≥1; Performance information of artificial intelligence (AI) models.

28. The method according to claim 27, characterized in that, Before the network-side device receives the first information, the method further includes: The network-side device sends at least one first reporting configuration information, which is used by the terminal to determine or report the interference information predicted by the terminal.

29. The method according to claim 27 or 28, characterized in that, Before the network-side device receives the first information, the method further includes: The network-side device sends a second reporting configuration information, which is associated with at least one first reporting configuration information. The second reporting configuration information is used by the terminal to determine or report the first information, and the first reporting configuration information is used by the terminal to determine or report the interference information predicted by the terminal.

30. The method according to any one of claims 27 to 29, characterized in that, The network-side device receives the first information, including: The network-side device periodically receives the first information; The reporting period for the first information satisfies one of the following: The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal. The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI). The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal. The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal. The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal. In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

31. The method according to any one of claims 27 to 30, characterized in that, Before the network-side device receives the first information, the method further includes: The network-side device sends information to trigger the terminal to report the first information.

32. The method according to any one of claims 27 to 31, characterized in that, The method further includes at least one of the following: Send a deactivation instruction message to instruct the terminal to activate the AI ​​model, or to instruct the terminal to activate the AI ​​model within a target time period; Receive deactivation request information, which is used to request the deactivation of the AI ​​model, or to request the deactivation of the AI ​​model within a target time period; Deactivate the AI ​​model; Receive deactivation notification information to notify that the AI ​​model has been deactivated or that the AI ​​model is unavailable, or to notify that the AI ​​model will be deactivated or that the AI ​​model will be unavailable within a target time period. Receive update request information to request an update to the AI ​​model.

33. The method according to any one of claims 27 to 32, characterized in that, The method further includes: The network-side device receives the terminal's capability information; The capability information is used to instruct the terminal to determine or report the capability of the first information.

34. A wireless communication device, characterized in that, include: The sending module is used to report the initial information; Wherein, the first information is used to indicate at least one of the following: The prediction accuracy for T1 interference information is T1≥1; The prediction accuracy of interference information within T2 time-domain units is T2≥1; Performance information of artificial intelligence (AI) models.

35. The apparatus according to claim 34, characterized in that, The sending module is specifically used for: The first piece of information is reported periodically; The reporting period for the first information satisfies one of the following: The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal. The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI). The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal. The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal. The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal. In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

36. A wireless communication device, characterized in that, include: The receiving module is used to receive the first information; Wherein, the first information is used to indicate at least one of the following: The prediction accuracy for T1 interference information is T1≥1; The prediction accuracy of interference information within T2 time-domain units is T2≥1; Performance information of artificial intelligence (AI) models.

37. The apparatus according to claim 36, characterized in that, The receiving module is specifically used for: The first information is received periodically; The reporting period for the first information satisfies one of the following: The reporting period for the first information is determined based on the reporting period for the interference information predicted by the terminal. The reporting period for the first information is determined based on the reporting period for Channel State Information (CSI). The first reporting period of the first information is later than or equal to the first reporting period of the interference prediction information predicted by the terminal. The reporting period of the first information is greater than or equal to the reporting period of the interference information predicted by the terminal. The first reporting period of the first information has a first offset value relative to the first reporting period of the channel state information (CSI) or the first reporting period of the interference information predicted by the terminal. In the first reporting period of the first information, there is a second offset value in the first time domain unit of the system frame with system frame number SFN of 0.

38. A terminal, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the wireless communication method as described in any one of claims 1 to 26.

39. A network-side device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the wireless communication method as described in any one of claims 27 to 33.

40. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the wireless communication method as described in any one of claims 1 to 26, or implement the steps of the wireless communication method as described in any one of claims 27 to 33.

Images