Method, terminal device and network device for transmitting configuration information

Abstract

Provided are a method, a terminal device, and a network device for transmitting configuration information. The method includes: the terminal device receiving first configuration information transmitted by the network device, the first configuration information being used to configure one or more of the following for a first bandwidth part (BWP): a first model; a first artificial intelligence (AI) function; and a first AI feature. In embodiments of the present application, the network device can configure the terminal device with first configuration information for the first BWP, the first configuration information being used to configure one or more of the following: a first model; a first artificial intelligence (AI) function; and a first AI feature. Compared with a scheme in which the network device uniformly configures the terminal device in a conventional scheme, the scheme can help improve the accuracy of the configuration.

Description

Method, terminal device and network device for transmitting configuration information Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a method for transmitting configuration information, a terminal device, and a network device. Background Art

[0002] In some known technologies, network devices configure configuration information related to artificial intelligence (AI) and / or machine learning (ML) to terminal devices. Traditionally, network devices use a unified configuration approach. That is, the network device sends unified configuration information to all terminal devices within the coverage area of ​​the network device. However, this unified configuration approach may result in some terminal devices not being able to use the corresponding configuration, reducing the accuracy of the configuration.

[0003] Summary of the Invention

[0004] The present application provides a method, terminal device, and network device for transmitting configuration information. The following introduces various aspects of the present application.

[0005] In a first aspect, a method for transmitting configuration information is provided, including: a terminal device receives first configuration information sent by a network device, wherein the first configuration information is used to configure one or more of the following for a first bandwidth part (BWP): a first model; a first artificial intelligence (AI) function; and a first AI characteristic.

[0006] According to a second aspect, a method for transmitting configuration information is provided, including: a network device sends first configuration information to a terminal device, wherein the first configuration information is used to configure one or more of the following for a first bandwidth part BWP: a first model; a first artificial intelligence AI function; a first AI characteristic.

[0007] According to a third aspect, a terminal device is provided, including: a receiving unit for receiving first configuration information sent by a network device, wherein the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: a first model; a first artificial intelligence AI function; a first AI characteristic.

[0008] In a fourth aspect, a network device is provided, including: a sending unit for sending first configuration information to a terminal device, wherein the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: a first model; a first artificial intelligence AI function; a first AI characteristic.

[0009] In a fifth aspect, a terminal device is provided, comprising a processor, a memory, and a communication interface, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the terminal device executes part or all of the steps in the method of the first aspect.

[0010] In a sixth aspect, a network device is provided, comprising a processor, a memory, and a transceiver, wherein the memory is used to store one or more computer programs, and the processor is used to call the computer program in the memory so that the network device executes part or all of the steps in the method of the second aspect.

[0011] In a seventh aspect, an embodiment of the present application provides a communication system, which includes the above-mentioned terminal device and / or network device. In another possible design, the system may also include other devices that interact with the terminal device or network device in the solution provided in the embodiment of the present application.

[0012] In an eighth aspect, an embodiment of the present application provides a computer-readable storage medium, which stores a computer program, and the computer program enables a communication device (for example, a terminal device or a network device) to execute part or all of the steps in the methods of the above aspects.

[0013] In a ninth aspect, embodiments of the present application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program is operable to cause a communication device (e.g., a terminal device or a network device) to perform some or all of the steps of the methods described in each of the above aspects. In some implementations, the computer program product can be a software installation package.

[0014] In the tenth aspect, an embodiment of the present application provides a chip, which includes a memory and a processor. The processor can call and run a computer program from the memory to implement some or all of the steps described in the methods of the above aspects.

[0015] In an embodiment of the present application, a network device can configure first configuration information for a first BWP for a terminal device. This first configuration information is used to configure one or more of the following: a first model; a first artificial intelligence (AI) function; or a first AI feature. Compared to traditional solutions, a solution in which the network device performs unified configuration for the terminal device helps improve configuration accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] FIG1 is a wireless communication system 100 used in an embodiment of the present application.

[0017] FIG2 is a schematic diagram of a neural network applicable to an embodiment of the present application.

[0018] FIG3 is a schematic diagram of a convolutional neural network (CNN) applicable to an embodiment of the present application.

[0019] FIG4 is a schematic diagram of a channel state information (CSI) feedback system based on an AI model applicable to an embodiment of the present application.

[0020] Figure 5 is a schematic diagram of an AI model-based positioning solution applicable to an embodiment of the present application.

[0021] Figure 6 is a schematic diagram of AI model-based beam management applicable to an embodiment of the present application.

[0022] FIG7( a ) is a schematic diagram of the switching process of the model applicable to the embodiment of the present application.

[0023] Figure 7(b) is a schematic diagram of the switching process of the AI ​​function applicable to the embodiment of the present application.

[0024] FIG7( c ) is a schematic diagram of the switching process of the AI ​​feature applicable to the embodiment of the present application.

[0025] FIG8 is a schematic flowchart of a method for transmitting configuration information according to an embodiment of the present application.

[0026] FIG9 is a schematic diagram of four BWPs according to an embodiment of the present application.

[0027] FIG10 is a schematic diagram of a BWP switching process from BWP1 to BWP2 according to an embodiment of the present application.

[0028] FIG11 is a schematic diagram of a BWP switching process from BWP1 to BWP2 according to another embodiment of the present application.

[0029] FIG12 is a schematic diagram of a BWP switching process from BWP2 to BWP1 according to another embodiment of the present application.

[0030] FIG13 is a schematic diagram of a BWP switching process from BWP2 to BWP1 according to another embodiment of the present application.

[0031] FIG14 is a schematic diagram of a terminal device according to an embodiment of the present application.

[0032] FIG15 is a schematic diagram of a network device according to an embodiment of the present application.

[0033] FIG16 is a schematic structural diagram of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] The technical solution in this application will be described below with reference to the accompanying drawings.

[0035] Figure 1 illustrates a wireless communication system 100 used in an embodiment of the present application. The wireless communication system 100 may include a network device 110 and a terminal device 120. The network device 110 may be a device that communicates with the terminal device 120. The network device 110 may provide communication coverage for a specific geographic area and may communicate with the terminal device 120 within the coverage area.

[0036] FIG1 exemplarily shows a network device and two terminals. Optionally, the wireless communication system 100 may include multiple network devices and each network device may include other numbers of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0037] Optionally, the wireless communication system 100 may further include other network entities such as a network controller and a mobility management entity, which is not limited in the embodiment of the present application.

[0038] It should be understood that the technical solutions of the embodiments of the present application can be applied to various communication systems, such as: fifth generation (5G) system or new radio (NR), long term evolution (LTE) system, LTE frequency division duplex (FDD) system, LTE time division duplex (TDD), etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system, satellite communication system, etc.

[0039] The terminal device in the embodiments of the present application may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station (MS), mobile terminal (MT), remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent or user device. The terminal device in the embodiments of the present application may refer to a device that provides voice and / or data connectivity to a user and can be used to connect people, objects and machines, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. The terminal device in the embodiments of the present application can be a mobile phone, a tablet computer, a laptop computer, a PDA, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, etc. Optionally, the UE can be used to act as a base station. For example, the UE can act as a scheduling entity that provides sidelink signals between UEs in V2X or D2D, etc. For example, a cellular phone and a car communicate with each other using sidelink signals. The cellular phone and smart home devices communicate without relaying the communication signal through the base station.

[0040] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. A base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station MeNB, secondary station SeNB, multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), positioning node, etc. A base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. A base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs base station functions in device-to-device D2D, vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. The base station can support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the network equipment.

[0041] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and one or more cells can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0042] In some deployments, the network device in the embodiments of the present application may refer to a CU or a DU, or the network device may include a CU and a DU. The gNB may also include an AAU.

[0043] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0044] It should be understood that all or part of the functions of the communication device in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (such as a cloud platform).

[0045] With the development of AI technology, AI models are increasingly being incorporated into communication processes. In some scenarios, AI models based on machine learning (ML) are also referred to as "ML models." For easier understanding, the following describes AI models used in communication processes, using Figures 2 and 3.

[0046] AI models

[0047] In recent years, artificial intelligence research, exemplified by neural networks, has achieved remarkable success in many fields, and will continue to play a vital role in people's lives and production for a long time to come. A neural network can be understood as a computational model consisting of multiple interconnected neuron nodes. The connections between these nodes represent the weighted values ​​from input signals to output signals, often referred to as weights. Each node performs a weighted summation of different input signals and outputs the result through a specific activation function.

[0048] Common neural networks include CNN, recurrent neural network (RNN), deep neural network (DNN), etc.

[0049] The following describes a neural network applicable to embodiments of the present application in conjunction with FIG2 . The neural network shown in FIG2 can be divided into three categories based on the location of different layers: input layer 210 , hidden layer 220 , and output layer 230 . Generally speaking, the first layer is the input layer 210 , the last layer is the output layer 230 , and the intermediate layers between the first and last layers are all hidden layers 220 .

[0050] The input layer 210 is used to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layer 220 is used to process the input data, for example, decompress the received signal. The output layer 230 is used to output processed output data, for example, a decompressed signal.

[0051] As shown in Figure 2, a neural network consists of multiple layers, each of which contains multiple neurons. The neurons between layers can be fully connected or partially connected. For connected neurons, the output of the neurons in the previous layer can serve as the input of the neurons in the next layer.

[0052] With the continuous advancement of neural network research, deep learning algorithms have been proposed in recent years. These algorithms introduce a large number of hidden layers into neural networks, forming DNNs. More hidden layers allow DNNs to better capture complex real-world situations. Theoretically, a model with more parameters has higher complexity and a greater "capacity," meaning it can handle more complex learning tasks. These neural network models are widely used in pattern recognition, signal processing, optimization and combination, anomaly detection, and other fields.

[0053] CNN is a deep neural network with a convolutional structure. Its structure is shown in Figure 3 and may include an input layer 310, a convolutional layer 320, a pooling layer 330, a fully connected layer 340, and an output layer 350.

[0054] Each convolution layer 320 may include a plurality of convolution operators, which are also called kernels. The convolution operator can be regarded as a filter for extracting specific information from the input signal. The convolution operator can essentially be a weight matrix, which is usually predefined.

[0055] The weight values ​​in these weight matrices need to be obtained through a lot of training in practical applications. The weight matrices formed by the weight values ​​obtained through training can extract information from the input signal, thereby helping CNN to make correct predictions.

[0056] When CNN has multiple convolutional layers, the initial convolutional layer tends to extract more general features, which can also be called low-level features. As the depth of CNN increases, the features extracted by the subsequent convolutional layers become more and more complex.

[0057] Pooling layers 330 are often used periodically after convolutional layers to reduce the number of training parameters. For example, a single convolutional layer can be followed by a single pooling layer, as shown in Figure 3, or multiple convolutional layers can be followed by one or more pooling layers. In signal processing, the sole purpose of a pooling layer is to reduce the spatial size of the extracted information.

[0058] The fully connected layer 340, after being processed by the convolution layer 320 and the pooling layer 330, is not sufficient for CNN to output the required output information. Because as mentioned above, the convolution layer 320 and the pooling layer 330 only extract features and reduce the parameters brought by the input data. However, in order to generate the final output information (for example, the bit stream of the original information transmitted by the transmitter), CNN also needs to use the fully connected layer 340. Generally, the fully connected layer 340 may include multiple hidden layers, and the parameters contained in the multiple hidden layers may be pre-trained based on relevant training data of a specific task type. For example, the task type may include decoding a data signal received by a receiver. For another example, the task type may also include channel estimation based on a pilot signal received by the receiver.

[0059] Following the multiple hidden layers in the fully connected layer 340, the final layer of the CNN is the output layer 350, which is used to output the results. Typically, this output layer 350 is configured with a loss function (e.g., a loss function similar to categorical cross entropy) to calculate the prediction error, or to evaluate the degree of difference between the CNN model's output (also known as the predicted value) and the ideal result (also known as the true value).

[0060] To minimize the loss function, the CNN model needs to be trained. In some implementations, the CNN model can be trained using a backpropagation algorithm (BP). The BP training process consists of a forward propagation process and a backward propagation process. During the forward propagation process (e.g., the propagation from 310 to 350 in Figure 3 is forward propagation), the input data is fed into the aforementioned layers of the CNN model, processed layer by layer, and transmitted to the output layer. If the output result differs significantly from the ideal result, the minimization of the aforementioned loss function is used as the optimization goal, and the backward propagation process is switched to (e.g., the propagation from 350 to 310 in Figure 3 is backward propagation). The partial derivatives of the optimization goal with respect to each neuron weight are calculated layer by layer, forming the gradient of the optimization goal with respect to the weight vector, which serves as the basis for modifying the model weights. The CNN training process is completed during the weight modification process. When the aforementioned error reaches the desired value, the CNN training process ends.

[0061] It should be noted that the CNN shown in Figure 3 is only an example of a convolutional neural network. In specific applications, the convolutional neural network can also exist in the form of other network models, and the embodiments of the present application are not limited to this.

[0062] RNNs are designed to process sequential data. In traditional neural network models (for example, CNN models), the layers are fully connected, from the input layer to the hidden layer to the output layer, and the nodes within each layer are disconnected. However, these ordinary neural networks are inadequate for many problems. For example, if you want to predict the next word in a sentence, you generally need to use the previous word, because the previous and next words in a sentence are not independent. RNNs are called recurrent neural networks because the current output of a sequence is also related to the previous output. Specifically, the network remembers the previous information and applies it to the calculation of the current output. That is, the nodes between hidden layers are no longer disconnected but connected, and the input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the previous moment. In theory, RNNs can process sequence data of any length.

[0063] Training an RNN is similar to training a traditional ANN (artificial neural network). The same backpropagation error algorithm is used, but there is a slight difference. If the RNN is expanded, the parameters W, U, and V are shared, while traditional neural networks are not. Furthermore, when using the gradient descent algorithm, the output of each step depends not only on the network state at the current step, but also on the state of the network at the previous steps. For example, at t = 4, three steps need to be propagated backward, and various gradients need to be added to the three subsequent steps. This learning algorithm is called backpropagation through time (BPTT).

[0064] Given the existence of artificial neural networks and convolutional neural networks, why do we still need recurrent neural networks? The reason is simple. Both convolutional and artificial neural networks assume that elements are independent of each other, and that inputs and outputs are also independent, like cats and dogs. However, in the real world, many elements are interconnected, such as the changes in stock prices over time. For example, someone said, "I love traveling, and my favorite place is Yunnan. I must visit __ someday." Everyone knows to fill in the blank with "Yunnan." This is because we infer this information based on the context, but achieving this is quite difficult. Therefore, recurrent neural networks were developed. Their essence is that they possess memory, just like humans. Therefore, their output depends on the current input and memory.

[0065] The AI ​​model applicable to the embodiments of the present application is described above with reference to Figures 2 to 3. The communication process of introducing the AI ​​model is described below with reference to Figures 4 to 6.

[0066] CSI feedback system based on AI model

[0067] In wireless communication systems, codebook-based solutions are primarily used to extract and provide feedback on channel characteristics. This means that after the receiver performs channel estimation, it selects the precoding matrix that best matches the current channel from a pre-set precoding codebook based on the estimation results and an optimization criterion. The receiver then feeds the precoding matrix index (PMI) back to the transmitter via an air interface feedback link for precoding. In some implementations, the receiver can also provide the transmitter with a measured channel quality indicator (CQI) to facilitate adaptive modulation and coding.

[0068] Figure 4 is a schematic diagram of a CSI feedback system based on an AI model applicable to an embodiment of the present application. As shown in Figure 4, the entire feedback system includes an AI encoder 411 and an AI decoder 421 part of the autoencoder, wherein the AI ​​encoder 411 is deployed at the transmitter 410 and the AI ​​decoder 421 is deployed at the receiver 420. The transmitter 410 compresses and encodes the CSI to be transmitted through the AI ​​encoder 411 to obtain compressed CSI. The compressed CSI is then fed back to the receiver 420 through the feedback link, and the receiver 420 decodes the compressed CSI through the AI ​​decoder 421 to obtain the recovered CSI. In this way, the communication overhead of feedback CSI can be saved without affecting the accuracy of CSI transmission.

[0069] Positioning based on AI models

[0070] In cellular wireless positioning, the straight-line propagation of electromagnetic waves between network devices and end devices is called line-of-sight (LOS) wireless propagation. In some cases, electromagnetic wave signals cannot propagate in a straight line due to obstruction by buildings or trees, which is commonly referred to as non-line-of-sight (NLOS) wireless propagation. Traditional positioning algorithms, such as time difference of arrival (TDOA) and angle-of-arrival (AOA), are based on LOS channels and are no longer applicable in NLOS-dominated environments. In most scenarios, the number of network devices with LOS channels to end devices is often small, resulting in the inability of traditional positioning algorithms to meet the requirements for high-precision positioning. Furthermore, actual systems may also contain non-ideal factors that can reduce positioning accuracy.

[0071] Therefore, a high-precision positioning method based on AI models has been proposed for scenarios where LOS / NLOS channels coexist. Existing research results have shown that by using machine learning methods to train models based on large amounts of channel data and to explore the mapping relationship between channel responses and location coordinates, it is possible to address the limitations of traditional positioning algorithms in LOS / NLOS channel coexistence scenarios and improve positioning accuracy.

[0072] FIG5 shows a schematic diagram of an AI model-based positioning solution applicable to an embodiment of the present application. Referring to FIG5 , in a positioning solution based on an AI model 510 in a LOS / NLOS channel coexistence scenario, the channel response can be used as the input of the AI ​​model 510, and the location coordinates can be used as the output of the AI ​​model 510. The AI ​​model 510 learns the intrinsic relationship between the wireless channel and the location of the terminal device. In this way, even in a scenario where there are not enough LOS channels and / or in a scenario where there are non-ideal conditions, the positioning solution based on the AI ​​model 510 can also output the location coordinates of the terminal device with higher accuracy, which helps to meet the needs of high-precision positioning.

[0073] The above introduces several communication processes applicable to the AI ​​model. The following introduces the AI ​​model applicable to the embodiments of the present application. It should be noted that the AI ​​model applicable to the embodiments of the present application is not limited to the several AI models introduced below.

[0074] AI-based beam management

[0075] In the traditional beam selection process, it is usually necessary to traverse all combinations of receive beams and transmit beams to select the appropriate beam. However, traversing all combinations takes a long time, resulting in low beam selection efficiency.

[0076] For example, suppose the network equipment deploys 64 different downlink transmission directions in FR2 (carried by up to 64 synchronization signals and physical broadcast channel blocks (SSB)). Accordingly, the terminal device uses one or more antenna panels to simultaneously scan the receiving beams when receiving, and each antenna panel has 4 receiving beams. Then the terminal device needs to measure at least 256 beam pairs, which means that 256 resources of downlink resource overhead are required. From a time perspective, each SSB cycle is approximately 20ms, and 4 SSB cycles are required to complete the measurement of 4 receiving beams. Assuming that multiple receiving antenna panels can perform beam scanning simultaneously, it will take at least 80ms.

[0077] As the number of beams in future massive multiple-input, multiple-output (MIMO) systems increases, using beam scanning-based beam management solutions to match optimal beam pairs will only result in increased reference signal transmission overhead and beam scanning latency. Therefore, to avoid these issues, AI-based beam management was proposed in Release 18. The following describes this AI-based beam management solution, combining the training and prediction processes of the AI ​​model.

[0078] Assume that the AI ​​model is used to predict the available beams in beam set A. Accordingly, during the training phase, the beam measurement results of beam set B can be used as AI model training data. That is, the AI ​​model is trained based on the beam measurement results of beam set B so that the AI ​​model can predict the available beams from beam set A.

[0079] It should be noted that the beam measurement results of the above-mentioned beam set B may include the measurement results corresponding to the layer 1 (layer1, L1) measurement quantity, and / or the indication information of the selected beam in beam set B (for example, the transmitting beam identifier, the receiving beam identifier or the beam pair identifier, etc.).

[0080] In some implementations, the training data may also include label information of beam set A, and the label information is used to indicate one or more of the following beams in beam set A: optimal transmit beam, optimal receive beam, optimal beam pair, better multiple transmit beams, better multiple receive beams, better beam pair, etc.

[0081] As shown in Figure 6, in the prediction stage, the input of the AI ​​model 610 may include the link quality measurement results (for example, L1 measurement quantity) corresponding to the beams in the beam set A, and the prediction results output by the AI ​​model 610 may include the target beam selected from the beam set A, and the link quality corresponding to the target beam.

[0082] In some implementations, the target beam may be one or more beams. For example, if the target beam is a single beam, the target beam may be the optimal beam or a relatively optimal beam in beam set A. For example, if the target beam is multiple beams, the target beam may be multiple beams in beam set A that meet the requirements. "Meeting the requirements" may be understood as meaning that the link quality corresponding to the beam meets the requirements, for example, the link quality corresponding to the beam is greater than or equal to a threshold.

[0083] In other implementations, the target beam may refer to one or more beam pairs, each of which may include a receive beam or a transmit beam. For example, if the target beam is a single beam pair, the target beam may be the optimal beam pair or a relatively optimal beam pair in beam set A. For example, if the target beam is multiple beam pairs, the target beam may be multiple beam pairs in beam set A that meet the requirements. "Meeting the requirements" may be understood as meaning that the link quality corresponding to the beam pair meets the requirements, for example, the link quality corresponding to the beam pair is greater than or equal to a threshold.

[0084] It should be noted that the link quality in the embodiment of the present application can be determined by one or more measurement quantities described above. Of course, the link quality in the embodiment of the present application can also be determined based on other measurement quantities in future communication systems, and the embodiment of the present application is not limited to this.

[0085] In addition, the link quality is determined based on one or more measurement quantities, which can be understood as the link quality being obtained by processing one or more measurement quantities. Of course, the link quality can also be a measurement quantity, which is not limited in the present embodiment.

[0086] It should also be noted that if the prediction result only indicates one beam in the beam pair, the other beam in the beam pair can be determined by other means. For example, it can be determined by one or some of the processes P1 to P3 in the traditional beam selection process. Of course, it can also be determined by one or some of the processes U1 to U3 in the traditional beam selection process. The embodiments of the present application are not limited to this.

[0087] In some implementations, the beam set B may be a different beam set from the beam set A. In some implementations, the beam set B may be a subset of the beam set A. Accordingly, by measuring fewer beams (beams in the beam set B), predictions for more beams (beams in the beam set A) may be achieved. Compared with the above-mentioned scheme of selecting beams based on traversing all combinations, it helps to reduce the time of executing the beam selection process. Of course, in the embodiment of the present application, the beams in the beam set B and the beams in the beam set A may be completely different beams. For example, there is no intersection between the beam set B and the beam set A, but the beam direction corresponding to the beam set B may be similar to the beam direction corresponding to the beam set A.

[0088] In some other implementations, the beam set B may be exactly the same as the beam set A.

[0089] The process of selecting and activating models, AI features, and AI functionality

[0090] As mentioned above, models are introduced in some communication processes to further improve communication performance. In the embodiments of the present application, the model can be an AI model, for example, any of the AI ​​models described above. Of course, in the embodiments of the present application, the model can also be a model built based on machine learning in AI. Therefore, the AI ​​model can also be called an ML model, or an AI / ML model.

[0091] Some known technologies have discussed the selection and activation process for models, AI features, and AI functions. The following describes the model, AI features, and AI functions separately with reference to Figures 7(a) to 7(c).

[0092] 7( a ), the network device may configure a model set for the terminal device, where the model set may include model 1 and model 2. Thereafter, the network device may send an instruction message to the terminal device to activate a model from the model set.

[0093] Typically, different models may be suitable for different communication environments. Therefore, if the currently active model is no longer suitable for the current communication environment, a model switch is required, also known as model switching. For example, when a terminal device switches from one cell to another, the communication environment may change significantly. If the network device detects poor performance of Model 1, the network device can instruct the terminal device to switch from Model 1 to Model 2 through an instruction message.

[0094] As shown in FIG7( b ), the network device may configure an AI function set for the terminal device, where the AI ​​function set may include AI function 1 and AI function 2. Thereafter, the network device may send an instruction to the terminal device to activate one of the AI ​​functions in the AI ​​function set.

[0095] Typically, different AI functions may be suitable for different communication environments. Therefore, if the currently activated AI function is no longer suitable for the current communication environment, it is necessary to switch the AI ​​function. For example, when a terminal device switches from one cell to another, the communication environment may change significantly. If the network device detects poor performance of AI function 1, the network device can instruct the terminal device to switch from AI function 1 to AI function 2 through an indication message.

[0096] As shown in FIG7(c), the network device may configure an AI feature set for the terminal device, where the AI ​​feature set may include AI feature 1 and AI feature 2. Thereafter, the network device may send an instruction to the terminal device to activate one of the AI ​​features in the AI ​​feature set.

[0097] Typically, different AI features may be suitable for different communication environments. Therefore, if the currently activated AI feature is no longer suitable for the current communication environment, it is necessary to switch the AI ​​feature. For example, when a terminal device switches from one cell to another, the communication environment may change significantly. If the network device detects poor performance of AI Feature 1, the network device can instruct the terminal device to switch from AI Feature 1 to AI Feature 2 through an instruction message.

[0098] In some known technologies, network devices send configuration information related to AI and / or ML to terminal devices. In the traditional configuration process, network devices adopt a unified configuration method. For example, the network device configures a unified model for all terminal devices within the coverage area of ​​the network device. For another example, the network device configures a unified AI feature for all terminal devices within the coverage area of ​​the network device. For another example, the network device configures a unified AI function for all terminal devices within the coverage area of ​​the network device. However, based on this unified configuration method, some terminal devices may not be applicable to the corresponding configuration, reducing the accuracy of the configuration.

[0099] Applicants have discovered that terminal devices supporting different operating bandwidths require different AI and / or ML-related configurations. On the one hand, the larger the operating bandwidth, the more complex the communication environment, and accordingly, the more complex the adapted model. Taking the operating bandwidth as BWP as an example, assume that the frequency domain range corresponding to BWP1, operated by terminal device 1, is larger than the frequency domain range corresponding to BWP2, operated by terminal device 2, and the network device configures Model 1, a lower-complexity model, for both terminal device 1 and terminal device 2. In this case, for terminal device 2, if Model 1 is used on BWP2, the complexity of Model 1 can be adapted to the frequency domain range of BWP2. In this case, Model 1 has better model performance, resulting in higher communication quality for terminal device 2. For terminal device 1, if Model 1 is used on BWP1, the complexity of Model 1 is insufficient to cope with the frequency domain range of BWP2, and Model 1 may have poor model performance, resulting in poor communication quality for terminal device 1. Therefore, the above-mentioned unified configuration is not applicable to terminal device 1 operating on BWP1, reducing the accuracy of the configuration.

[0100] On the other hand, for BWPs with larger subcarrier spacing, the duration of the corresponding time-domain symbols is shorter. For example, if the subcarrier spacing for BWP1 is larger than that for BWP2, the length of the time-domain symbols in BWP1 is shorter than that in BWP2. Currently, the duration required for model inference is measured based on the number of time-domain symbols. Therefore, BWPs with larger subcarrier spacing require shorter model inference times than BWPs with smaller subcarrier spacing. Continuing with BWP1 and BWP2 as an example, assume that terminal device 1 operates on BWP1 and terminal device 2 operates on BWP2. The network device configures Model 1 for both terminal devices 1 and 2. Model 1 requires two time-domain symbols for a single model inference. In this case, for terminal device 2, if Model 1 is used on BWP2, the two time-domain symbols required for a single model inference run by Model 1 are the same as the two time-domain symbols required for BWP2. This means that Model 1 is applicable to terminal device 2. For terminal device 1, if model 1 is used on BWP1, the duration of two time-domain symbols required for model 1 to perform a model inference process is longer than the duration of two time-domain symbols corresponding to BWP1. In other words, the two time-domain symbols corresponding to BWP1 are not sufficient for model 1 to perform a model inference process. Therefore, model 1 is not applicable to terminal device 2. In this case, the above unified configuration is not applicable to terminal device 1 operating on BWP1, reducing the accuracy of the configuration.

[0101] Therefore, to address the above issues, embodiments of the present application provide a method for transmitting configuration information, in which network devices can be configured based on the operating bandwidth corresponding to terminal devices. Compared to a unified configuration solution, this method helps improve configuration accuracy. In embodiments of the present application, the operating bandwidth is not limited. For example, the operating bandwidth can be a frequency band. In another example, the operating bandwidth can be a bandwidth-width-preserving (BWP). In another example, the operating bandwidth can be the system bandwidth.

[0102] The following describes a method for transmitting configuration information according to an embodiment of the present application, taking the working bandwidth as BWP as an example, in conjunction with Figure 8. The method shown in Figure 8 includes step S810.

[0103] In step S810, the network device sends first configuration information to the terminal device, where the first configuration information is used to configure one or more of the following for the first BWP: a first model; a first AI function; or a first AI characteristic.

[0104] In some implementations, the first model may be an AI model, for example, any of the AI ​​models described above. Of course, in the embodiments of the present application, the model may also be a model built based on machine learning in AI, and therefore, the AI ​​model may also be referred to as an ML model, or an AI / ML model. It can be seen from this that one or more of the first model, the first AI function, and the first AI feature are all associated with AI, and therefore, the first configuration information may also be referred to as "first AI configuration information."

[0105] In some scenarios, for multiple BWPs, the network device can send configuration information for each of the multiple BWPs, which helps to improve the accuracy of the configuration information compared to the traditional unified configuration solution.

[0106] In the embodiment of the present application, the relationship between the configuration information corresponding to multiple BWPs is not limited. For example, the configuration information corresponding to multiple BWPs can be the same. For another example, the configuration information corresponding to multiple BWPs can be different.

[0107] In some implementations, the first configuration information is used to configure one or more of the following: the frequency domain location, bandwidth, and parameter set of the first BWP. That is, the first configuration information includes one or more of the following: the frequency domain location of the first BWP; the bandwidth of the first BWP; and the parameter set of the first BWP. Therefore, the first configuration information used to configure the first BWP is associated with the first BWP and, therefore, can also be referred to as "first BWP configuration information."

[0108] For example, the first configuration information includes the frequency domain location of the first BWP. In other words, the first configuration information is used to indicate the frequency domain location of the first BWP. For example, the first configuration information may include the frequency domain starting location of the first BWP. For another example, the first configuration information may include the frequency domain ending location of the first BWP.

[0109] For example, the first configuration information includes the frequency bandwidth of the first BWP, or in other words, the first configuration information is used to indicate the frequency domain width of the first BWP. For example, the first configuration information may carry the number of RBs occupied by the first BWP, and indicate the frequency domain width of the first BWP by the number of RBs.

[0110] Taking the first configuration information including the parameter set (numerology) of the first BWP as an example, in some implementations, the parameter set of the first BWP may include one or more of the following parameters: the subcarrier spacing of the first BWP; the cyclic prefix of the first BWP; and the identifier of the first BWP.

[0111] As mentioned above, the first BWP configuration information and the first AI configuration information can be carried in the same configuration information to simplify the transmission process of the configuration information. Of course, in the embodiment of the present application, the first BWP configuration information and the first AI configuration information can be carried in different configuration information.

[0112] The following describes the first configuration information in the embodiments of the present application in combination with Examples 1 to 3 respectively.

[0113] Embodiment 1: The first configuration information is used to configure a first model for a first BWP.

[0114] In some implementations, the first configuration information is used to configure the first model for the first BWP, which may be replaced by the first configuration information being used to indicate the first model supported by the first BWP, or in other words, the first configuration information is used to indicate a model not supported in the first BWP.

[0115] In an embodiment of the present application, the network device can configure a first model that matches a first BWP for the terminal device using the first configuration information. In other words, the first model is bundled with the first BWP, thereby helping to improve the communication quality of communications based on the first model over the first BWP. In addition, using the first configuration information to configure the first BWP with the matching first model helps to improve configuration accuracy, thereby reducing the overhead of transmitting the first configuration information.

[0116] In some implementations, the first configuration information may carry a model identifier of the first model, and the first model may be configured for the first BWP using the model identifier of the first model, thereby helping to reduce the overhead of transmitting the first configuration information. Of course, in an embodiment of the present application, the first configuration information may include the first model itself, for example, the first configuration information may include the model structure of the first model and the model parameters of the first model. Alternatively, the first configuration information may only include the model parameters of the first model. Accordingly, the terminal device may obtain the first model based on the preconfigured or predefined model structure of the first model and the model parameters of the first model obtained from the first configuration information.

[0117] In the embodiments of the present application, there is no limit on the number of models that can be configured by the first configuration information. For example, the first configuration information may be used to configure only one model for the first BWP, namely the first model. In another example, the first configuration information may be used to configure multiple models for the first BWP, where the multiple models may include the first model. The manner in which the multiple models are carried in the first configuration information is similar to the manner in which the first model is carried in the first configuration information described above. For the sake of brevity, this description will not be repeated here.

[0118] In some implementations, the first configuration information is used to configure one or more models for implementing an AI function (also referred to as a first AI function) for the first BWP, where the one or more models include the first model, thereby increasing the flexibility of implementing the first AI function on the first BWP. Of course, in embodiments of the present application, multiple models may also be used to implement different AI functions.

[0119] In some other implementations, the first configuration information is used to configure one or more models for implementing an AI feature (also referred to as the first AI feature) for the first BWP, where the one or more models include the first model, thereby increasing the flexibility of implementing the first AI feature on the first BWP. Of course, in the embodiments of the present application, multiple models may also be used to implement different AI features.

[0120] In some implementations, the first configuration information can also be used to configure a first default model for the first BWP, wherein activation of the first default model is in response to activation of the first BWP, that is, the first default model is activated by default (or automatically activated) at the same time as the first BWP is activated, which helps to reduce the signaling overhead required for model activation.

[0121] In the embodiments of the present application, the first default model is not limited. In some implementations, the first default model can be a model with relatively stable model performance, or in other words, the first default model can be a model with the highest reliability to ensure the communication quality of communication on the first BWP. Assuming that the models corresponding to the first BWP can include Model 1 and Model 2, and the average model inference accuracy of Model 1 is lower than the average model inference accuracy of Model 2, in this case, Model 2 can be used as the first default model. Generally, models with better generalization performance are applicable to a wider range of scenarios. Therefore, in other implementations, the first default model can be a model with the best generalization performance to ensure the communication quality of communication on the first BWP. Assuming that the models corresponding to the first BWP can include Model 1 and Model 2, and the generalization performance of Model 1 is higher than the generalization performance of Model 2, in this case, Model 1 can be used as the first default model.

[0122] In the embodiments of the present application, the manner in which the first configuration information configures the first default model is not limited. For example, if the first configuration information is used to configure the first model, the first model may be the first default model, that is, the first configuration information may be used to configure the first default model for the first BWP. For another example, if the first configuration information is used to configure multiple models, the first configuration information is also used to indicate the first default model from the multiple models. Of course, in the embodiments of the present application, the information indicating the first default model and the first configuration information may be different information, and the embodiments of the present application do not limit this.

[0123] The above describes how to activate the first default model in the embodiments of this application. The following describes how to activate other models configured for the first BWP. These other models may be models other than the first default model among the multiple models configured for the first BWP. It should be understood that the methods for activating other models described below can also be used to activate the first default model.

[0124] In some implementations, the above method also includes: the network device can send first indication information to the terminal device, wherein the first indication information is used to indicate the activation of other models among the multiple models, which helps to improve the flexibility of activating other models.

[0125] In some implementations, the duration of use of the aforementioned other models can be determined based on a first timer, helping to reduce the overhead of transmitting signaling instructions to stop using the other models. That is, the method further includes: in response to receiving the first indication information, the terminal device starting a first timer; while the first timer is running, the terminal device communicates with the network device based on the other models. Of course, in the embodiments of the present application, if the above issues are taken into consideration, the network device can instruct the terminal device to stop using the other models through the indication information.

[0126] In some implementations, other models are used for communication between terminal devices and network devices. Therefore, the network device may also need to know when to activate other models and when to deactivate other models. Accordingly, in an embodiment of the present application, the network device may also maintain a first timer, and the start and running time of the first timer are similar to those of the first timer maintained by the terminal device. For example, the above method also includes: in response to sending the first indication information, the network device starts the first timer; during the operation of the first timer, the network device communicates with the terminal device based on the other model.

[0127] In the embodiment of the present application, the first timer is not limited. For example, the first timer can be a first countdown timer. Accordingly, in response to receiving the first indication information, the terminal device starts the first countdown timer, and during the operation of the first countdown timer, the terminal device communicates with the network device based on other models.

[0128] In some implementations, if the usage period of other models expires, the terminal device can fall back from the other models to the first default model and communicate based on the first default model. Of course, in the embodiments of the present application, the model to which it falls back is not limited. For example, the model to which it falls back can be a model other than the first default model among the multiple models configured for the first BWP. In other words, the above method further includes: in response to the first timer expiring, the terminal device communicating with the network device based on the first default model.

[0129] As mentioned above, for the first timer maintained by the network device, the above method also includes: in response to the first timer timing out, the network device communicates with the terminal device based on the first default model.

[0130] In the embodiment of the present application, the first timer is not limited. For example, the first timer can be a first countdown timer. Accordingly, in response to the first countdown timer being reduced to 0, the terminal device communicates with the network device based on the first default model.

[0131] For example, the network device configures multiple models for the first BWP, including model 1 and model 2, wherein model 2 serves as the first default model. The average model reasoning accuracy of model 1 is less than the average model reasoning accuracy of model 2, and the model reasoning duration of model 1 is less than the model reasoning duration of model 2. Accordingly, the network device can instruct the terminal device to activate model 1 through the first indication information. Accordingly, after receiving the first indication information, the terminal device activates the first timer and communicates based on model 1 while the first timer is running. That is to say, when the model reasoning accuracy requirement is not too high, model 1 can be used for model reasoning to reduce the duration of model reasoning. Afterwards, when the first timer times out, the terminal device falls back from model 1 to model 2, and continues to communicate based on model 2 to ensure the accuracy of model reasoning.

[0132] In some implementations, the duration of use of the first default model can also be determined based on a timer. Taking timer 1 as an example, the method further includes: in response to activating the first BWP, starting timer 1, and during the operation of timer 1, the terminal device communicates with the network device based on the first default model. Accordingly, timer 1 can be maintained on the terminal device and / or the network device.

[0133] Of course, in an embodiment of the present application, the usage duration of the first default model can also be determined based on the indication information sent by the network device. For example, the network device can send indication information to the terminal device to instruct the deactivation of the first default model.

[0134] In some implementations, if the network device sends a first indication to the terminal device during the execution of Timer 1, other models may be activated based on the first indication. The use of other models can be found in the previous description of Timer 1. This will be described below in conjunction with Figures 12 and 13 and will not be repeated here for the sake of brevity.

[0135] It should be noted that, in the embodiment of the present application, Timer 1 corresponding to the first default model can be understood as the timer corresponding to BWP1. That is, the usage duration of BWP1 can be determined based on Timer 1. In other words, in response to activation of BWP1, Timer 1 is started, and while Timer 1 is running, BWP1 is used for communication. In addition, in response to timer 1 timing out, BWP1 is deactivated.

[0136] In some implementations, if BWP1 is deactivated, the first configuration information corresponding to BWP1 is also deactivated. In this case, timer 1 may be the fourth timer described below. Of course, in the embodiment of the present application, the deactivation of the first configuration information may also be indicated by the network device through additional information.

[0137] Embodiment 2: The first configuration information is used to configure a first AI function for a first BWP.

[0138] In some implementations, the first configuration information is used to configure the first AI function for the first BWP, which can be replaced by the first configuration information being used to indicate the first AI function supported by the first BWP, or in other words, the first configuration information is used to indicate an AI function not supported in the first BWP.

[0139] In an embodiment of the present application, the network device can configure a first AI function that matches a first BWP for a terminal device using the first configuration information. In other words, bundling the first AI function with the first BWP helps improve the communication quality of communications based on the first AI function over the first BWP. In addition, using the first configuration information to configure the first AI function that matches the first BWP helps improve configuration accuracy and reduces the overhead of transmitting the first configuration information.

[0140] In some implementations, the AI ​​function can be understood as a communication function implemented based on AI. In some scenarios, AI can be implemented based on ML. Therefore, the above AI function can also be referred to as an "ML function" or "AI / ML function." For example, the first AI function includes a CSI feedback function implemented based on AI. For another example, the first AI function includes a positioning function implemented based on AI. For another example, the first AI function includes a beam management function implemented based on AI.

[0141] In some implementations, the first configuration information may carry an AI function identifier of the first AI function, and the first AI function may be configured for the first BWP using the AI ​​function identifier of the first AI function, thereby helping to reduce the overhead of transmitting the first configuration information.

[0142] In the embodiments of the present application, there is no limit on the number of AI functions configured by the first configuration information. For example, the first configuration information may be used to configure only one AI function, namely, the first AI function, for the first BWP. In another example, the first configuration information may be used to configure multiple AI functions for the first BWP, where the multiple AI functions may include the first AI function. The manner in which the multiple AI functions are carried in the first configuration information is similar to the manner in which the first AI function is carried in the first configuration information described above. For the sake of brevity, this description will not be repeated here.

[0143] In some implementations, the first configuration information can also be used to configure a first default AI function for the first BWP, wherein activation of the first default AI function is in response to activation of the first BWP, that is, the first default AI function is activated by default (or automatically activated) when the first BWP is activated, which helps to reduce the signaling overhead required for the AI ​​function activation process.

[0144] In the embodiments of the present application, the first default AI function is not limited. In some implementations, the first default AI function may be an AI function that is more generally applicable to the scenario, or the first default AI function may be an AI function with better reliability, or the first default AI function may be an AI function with better generalization performance to ensure the communication quality of the communication on the first BWP. Taking the AI ​​function configured for the first BWP as an AI-based positioning function as an example, the AI ​​functions configured for the first BWP may include an AI-based indoor positioning function, an AI-based outdoor positioning function, and an AI-based general scene positioning, wherein the AI-based general scene positioning can be applicable to the positioning process of indoor scenes and the positioning process of outdoor scenes. At this time, the AI-based general scene positioning can be used as the first default AI function.

[0145] In the embodiments of the present application, the manner in which the first configuration information configures the first default AI function is not limited. For example, if the first configuration information is used to configure the first AI function, the first AI function may be the first default AI function, that is, the first configuration information may be used to configure the first default AI function for the first BWP. For another example, if the first configuration information is used to configure multiple AI functions, the first configuration information may also be used to indicate the first default AI function from among the multiple AI functions. Of course, in the embodiments of the present application, the information indicating the first default AI function and the first configuration information may be different information, and the embodiments of the present application do not limit this.

[0146] The above describes the activation method for the first default AI function in the embodiments of the present application. The following describes the activation method for other AI functions configured for the first BWP. These other AI functions may be other AI functions other than the first default AI function among the multiple AI functions configured for the first BWP. It should be understood that the activation method for other AI functions described below can also be used to activate the first default AI function.

[0147] In some implementations, the above method also includes: the network device can send second indication information to the terminal device, wherein the second indication information is used to indicate the activation of other AI functions among the multiple AI functions, which helps to improve the flexibility of activating other AI functions.

[0148] In some implementations, the duration of use of the aforementioned other AI functions can be determined based on a second timer, helping to reduce the overhead of transmitting signaling instructing the cessation of use of the other AI functions. In other words, the method further includes: in response to receiving the second indication information, the terminal device starts a second timer; while the second timer is running, the terminal device communicates with the network device based on the other AI functions. Of course, in the embodiments of the present application, if the above issues are taken into consideration, the network device can instruct the terminal device to stop using the other AI functions through the indication information.

[0149] In some implementations, other AI functions are used for communication between the terminal device and the network device. Therefore, the network device may also need to know when to activate other AI functions and when to deactivate other AI functions. Accordingly, in an embodiment of the present application, the network device may also maintain a second timer, and the start and running time of the second timer are similar to those of the second timer maintained by the terminal device. For example, the above method also includes: in response to sending the second indication information, the network device starts the second timer; during the operation of the second timer, the network device communicates with the terminal device based on the other AI functions.

[0150] In the embodiments of the present application, the second timer is not limited. For example, the second timer can be a second countdown timer. Accordingly, in response to receiving the second indication information, the terminal device starts the second countdown timer, and during the operation of the second countdown timer, the terminal device communicates with the network device based on other AI functions.

[0151] In some implementations, if the usage period of other AI functions expires, the terminal device can fall back from the other AI functions to the first default AI function and communicate based on the first default AI function. Of course, in the embodiments of the present application, the AI ​​function to fall back to is not limited. For example, the AI ​​function to fall back to can be an AI function other than the first default AI function among the multiple AI functions configured for the first BWP. In other words, the above method further includes: in response to the second timer expiring, the terminal device communicating with the network device based on the first default AI function.

[0152] As mentioned above, for the second timer maintained by the network device, the above method also includes: in response to the second timer timing out, the network device communicates with the terminal device based on the first default AI function.

[0153] In the embodiment of the present application, the second timer is not limited. For example, the second timer can be a second countdown timer. Accordingly, in response to the second countdown timer being reduced to 0, the terminal device communicates with the network device based on the first default AI function.

[0154] For example, the multiple AI functions configured by the network device for the first BWP include an AI-based indoor positioning function and an AI-based general scene positioning function, wherein the AI-based general scene positioning function serves as the first default AI function. Accordingly, if the network device detects that the terminal device enters the room, the network device may instruct the terminal device to activate the AI-based indoor positioning function through a second indication message. Accordingly, after receiving the second indication message, the terminal device activates the second timer and performs positioning based on the AI-based indoor positioning function while the second timer is running. When the second timer times out, the terminal device falls back from the AI-based indoor positioning function to the AI-based general scene positioning function, and continues to perform positioning based on the AI-based general scene positioning function.

[0155] In some implementations, the usage duration of the first default AI function can also be determined based on a timer. Taking Timer 2 as an example, the method further includes: in response to activating the first BWP, starting Timer 2, and during the running of Timer 2, the terminal device communicates with the network device based on the first default AI function. Accordingly, Timer 2 can be maintained on the terminal device and / or the network device.

[0156] Of course, in an embodiment of the present application, the usage duration of the first default AI function can also be determined based on the indication information sent by the network device. For example, the network device can send indication information to the terminal device to instruct the deactivation of the first default AI function.

[0157] In some implementations, if the network device sends a second indication to the terminal device during the execution of Timer 2, other AI functions may be activated based on the second indication. For details on the use of other AI functions, see the previous description of the second timer. This will be described below in conjunction with Figures 12 and 13 and will not be repeated here for the sake of brevity.

[0158] It should be noted that in this embodiment of the present application, Timer 2 corresponding to the first default AI function can be understood as the timer corresponding to BWP1. In other words, the usage duration of BWP1 can be determined based on Timer 2. In other words, in response to activation of BWP1, Timer 2 is started, and while Timer 2 is running, BWP1 is used for communication. In addition, in response to timer 2 timing out, BWP1 is deactivated.

[0159] In some implementations, if BWP1 is deactivated, the first configuration information corresponding to BWP1 is also deactivated. In this case, timer 2 may be the fourth timer described below. Of course, in the embodiment of the present application, the deactivation of the first configuration information may also be indicated by the network device through additional information.

[0160] Embodiment 3: The first configuration information is used to configure the first AI feature for the first BWP.

[0161] In some implementations, the first configuration information is used to configure the first AI feature for the first BWP. Alternatively, the first configuration information is used to indicate the first AI feature supported by the first BWP. Alternatively, the first configuration information is used to indicate an AI feature not supported in the first BWP.

[0162] In this embodiment of the present application, the network device can configure a first AI feature that matches a first BWP for the terminal device using the first configuration information. In other words, bundling the first AI feature with the first BWP helps improve the communication quality of communications over the first BWP based on the first AI feature. Furthermore, using the first configuration information to configure the first AI feature that matches the first BWP helps improve configuration accuracy and reduces the overhead of transmitting the first configuration information.

[0163] In some implementations, AI features can be understood as features implemented based on AI in a communication system. In some scenarios, AI can be implemented based on ML. Therefore, the above AI features can also be referred to as "ML features" or "AI / ML features." For example, a first AI feature includes a CSI feedback feature implemented based on AI. For another example, a first AI feature includes a positioning feature implemented based on AI. For another example, a first AI feature includes a beam management feature implemented based on AI.

[0164] In some implementations, the first configuration information may carry an AI feature identifier of the first AI feature, and the first AI feature is configured for the first BWP using the AI ​​feature identifier of the first AI feature, which helps reduce the overhead of transmitting the first configuration information.

[0165] In the embodiments of the present application, there is no limit on the number of AI features that can be configured in the first configuration information. For example, the first configuration information may be used to configure only one AI feature, namely, the first AI feature, for the first BWP. In another example, the first configuration information may be used to configure multiple AI features for the first BWP, where the multiple AI features may include the first AI feature. The manner in which the multiple AI features are carried in the first configuration information is similar to the manner in which the first AI feature is carried in the first configuration information described above. For the sake of brevity, this description will not be repeated here.

[0166] In some implementations, the first configuration information can also be used to configure a first default AI feature for the first BWP, wherein activation of the first default AI feature is in response to activation of the first BWP. That is, the first default AI feature is activated by default (or automatically activated) at the same time as the first BWP is activated, which helps to reduce the signaling overhead required for the AI ​​feature activation process.

[0167] In the embodiments of the present application, the first default AI feature is not limited. In some implementations, the first default AI feature may be an AI feature that is more generally applicable to the scenario, or the first default AI feature may be an AI feature with better reliability, or the first default AI feature may be an AI feature with better generalization performance to ensure the communication quality of the communication on the first BWP. Taking the AI ​​feature configured for the first BWP as an AI-based positioning feature as an example, the AI ​​features configured for the first BWP may include an indoor positioning feature based on AI, an outdoor positioning feature based on AI, and a general scene positioning based on AI, wherein the general scene positioning based on AI can be applicable to the positioning process of indoor scenes and the positioning process of outdoor scenes. At this time, the general scene positioning based on AI can be used as the first default AI feature.

[0168] In the embodiments of the present application, the manner in which the first configuration information configures the first default AI feature is not limited. For example, if the first configuration information is used to configure the first AI feature, the first AI feature may be the first default AI feature, that is, the first configuration information may be used to configure the first default AI feature for the first BWP. For another example, if the first configuration information is used to configure multiple AI features, the first configuration information may also be used to indicate the first default AI feature from among the multiple AI features. Of course, in the embodiments of the present application, the information indicating the first default AI feature and the first configuration information may be different information, and this is not limited in the embodiments of the present application.

[0169] The above describes the activation method for the first default AI feature in the embodiments of the present application. The following describes the activation method for other AI features configured for the first BWP. The other AI features may be other AI features other than the first default AI feature among the multiple AI features configured for the first BWP. It should be understood that the activation method for other AI features described below can also be used to activate the first default AI feature.

[0170] In some implementations, the method further includes: the network device may send third indication information to the terminal device, wherein the third indication information is used to indicate activation of other AI features among the multiple AI features, thereby helping to improve the flexibility of activating other AI features.

[0171] In some implementations, the duration of use of the aforementioned other AI features can be determined based on a third timer, helping to reduce the overhead of signaling to stop using the other AI features. That is, the method further includes: in response to receiving the third indication information, the terminal device starting a third timer; while the third timer is running, the terminal device communicates with the network device based on the other AI features. Of course, in the embodiments of the present application, if the above issues are taken into consideration, the network device can instruct the terminal device to stop using the other AI features through the indication information.

[0172] In some implementations, other AI features are used for communication between terminal devices and network devices. Therefore, the network device may also need to know when to activate and deactivate other AI features. Accordingly, in an embodiment of the present application, the network device may also maintain a third timer, and the start and running time of the third timer are similar to those of the third timer maintained by the terminal device. For example, the above method further includes: in response to sending the third indication information, the network device starts the third timer; during the operation of the third timer, the network device communicates with the terminal device based on the other AI features.

[0173] In the embodiments of the present application, the third timer is not limited. For example, the third timer can be a third countdown timer. Accordingly, in response to receiving the third indication information, the terminal device starts the third countdown timer, and during the operation of the third countdown timer, the terminal device communicates with the network device based on other AI features.

[0174] In some implementations, if the usage period of other AI features expires, the terminal device can fall back from the other AI features to the first default AI feature and communicate based on the first default AI feature. Of course, in the embodiments of the present application, the AI ​​feature to fall back to is not limited. For example, the AI ​​feature to fall back to can be an AI feature other than the first default AI feature among the multiple AI features configured for the first BWP. In other words, the above method further includes: in response to the expiration of the third timer, the terminal device communicating with the network device based on the first default AI feature.

[0175] As mentioned above, for the third timer maintained by the network device, the above method also includes: in response to the third timer timing out, the network device communicates with the terminal device based on the first default AI feature.

[0176] In the embodiment of the present application, the third timer is not limited. For example, the third timer can be a third countdown timer. Accordingly, in response to the third countdown timer being reduced to 0, the terminal device communicates with the network device based on the first default AI feature.

[0177] For example, the multiple AI features configured by the network device for the first BWP include an AI-based indoor positioning feature and an AI-based general scene positioning feature, wherein the AI-based general scene positioning feature serves as the first default AI feature. Accordingly, if the network device detects that the terminal device enters the room, the network device may instruct the terminal device to activate the AI-based indoor positioning feature through a third indication message. Accordingly, after receiving the third indication message, the terminal device activates the third timer and performs positioning based on the AI-based indoor positioning feature during the operation of the third timer. When the third timer times out, the terminal device falls back from the AI-based indoor positioning feature to the AI-based general scene positioning feature, and continues to perform positioning based on the AI-based general scene positioning feature.

[0178] In some implementations, the duration of use of the first default AI feature can also be determined based on a timer. Taking timer 3 as an example, the method further includes: in response to activating the first BWP, starting timer 3, and during the running of timer 3, the terminal device communicates with the network device based on the first default AI feature. Accordingly, timer 3 can be maintained on the terminal device and / or the network device.

[0179] Of course, in the embodiment of the present application, the usage duration of the first default AI feature can also be determined based on the indication information sent by the network device. For example, the network device can send indication information to the terminal device to instruct the deactivation of the first default AI feature.

[0180] In some implementations, if the network device sends a third indication to the terminal device during the execution of timer 3, other AI features may be activated based on the third indication. For details on the use of other AI features, see the previous description of the third timer. This will be described below in conjunction with Figures 12 and 13 and will not be repeated here for the sake of brevity.

[0181] It should be noted that in this embodiment of the present application, timer 3 corresponding to the first default AI feature can be understood as the timer corresponding to BWP1. In other words, the usage duration of BWP1 can be determined based on timer 2. In other words, in response to activation of BWP1, timer 3 is started, and communication is performed using BWP1 while timer 3 is running. In addition, in response to timer 3 timing out, BWP1 is deactivated.

[0182] In some implementations, if BWP1 is deactivated, the first configuration information corresponding to BWP1 is also deactivated. In this case, timer 3 may be the fourth timer described below. Of course, in the embodiment of the present application, the deactivation of the first configuration information may also be indicated by the network device through additional information.

[0183] As previously described, network devices can be configured for BWPs. In some scenarios, if a BWP is activated for a terminal device, the terminal device can communicate based on the configuration information corresponding to the BWP. In other words, the method further includes: in response to activating the first BWP, the terminal device communicating with the network device based on the first configuration information.

[0184] In the embodiments of the present application, the scenario for activating the first BWP is not limited. For example, activation of the first BWP may be triggered by BWP switching, that is, activation of the first BWP includes the terminal device switching from a second BWP to the first BWP, where the second BWP is different from the first BWP. For another example, activation of the first BWP may be initial activation by a network device for a terminal device, that is, activation of the first BWP includes the network device instructing the terminal device to activate the first BWP, wherein the initial activation does not involve switching between multiple BWPs.

[0185] In some implementations, if the terminal device switches from the second BWP to the first BWP, the terminal device may correspondingly switch from the first configuration information corresponding to the second BWP to the first configuration information corresponding to the first BWP, where the first configuration information corresponding to the second BWP is used to configure the second BWP. Furthermore, the first configuration information corresponding to the second BWP functions similarly to the first configuration information used to configure the first BWP described above. For the sake of brevity, please refer to the description of the first configuration information above.

[0186] In some implementations, the duration for which the terminal device uses the first configuration information may be determined based on a fourth timer. For example, the method further includes: in response to activating the first BWP, the terminal device starting a fourth timer; and during the fourth timer, the terminal device communicating with the network device based on the first configuration information.

[0187] In the embodiment of the present application, the fourth timer is not limited. For example, the fourth timer can be a fourth countdown timer. Accordingly, in response to activating the first BWP, the terminal device starts the fourth countdown timer, and during the fourth countdown timer, the terminal device communicates with the network device based on the first configuration information.

[0188] In some implementations, the method further includes: in response to the fourth timer expiring, the terminal device communicating with the network device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI feature. In other words, when the fourth timer expires, the terminal device falls back to the third BWP and communicates based on the second configuration information corresponding to the third BWP. It should be understood that the second configuration information has similar functionality to the first configuration information. Please refer to the description of the first configuration information above; for the sake of brevity, this description will not be repeated below.

[0189] In the embodiment of the present application, the fourth timer is not limited. For example, the fourth timer may be a fourth countdown timer. Accordingly, in response to the fourth timer timing out, the fourth countdown timer may be reduced to 0. That is, in response to the fourth countdown timer being reduced to 0, the terminal device communicates with the network device based on the second configuration information.

[0190] In some implementations, the third BWP is a default BWP. Of course, in the embodiment of the present application, the third BWP may also be another BWP configured by the terminal device, which is not limited in the embodiment of the present application.

[0191] In some implementations, the third BWP may support multiple models, and the multiple models include a default model of the third BWP. After the terminal device falls back to the third BWP, communication may be performed based on the default model of the third BWP. Of course, in the embodiment of the present application, after the terminal device falls back to the third BWP, communication may be performed based on any one of the multiple models.

[0192] For example, if the second configuration information is used to configure a default model for the third BWP, the terminal device communicating with the network device based on the second configuration information includes: the terminal device communicating with the network device based on the default model in the third BWP configured by the second configuration information.

[0193] In some implementations, the third BWP may support multiple AI functions, and the multiple AI functions include the default AI function of the third BWP. After the terminal device falls back to the third BWP, communication can be performed based on the default AI function of the third BWP. Of course, in the embodiment of the present application, after the terminal device falls back to the third BWP, communication can be performed based on any one of the multiple AI functions.

[0194] For example, if the second configuration information is used to configure a default AI function for the third BWP, the terminal device communicating with the network device based on the second configuration information includes: the terminal device communicating with the network device based on the default AI function in the third BWP configured by the second configuration information.

[0195] In some implementations, the third BWP may support multiple AI features, and the multiple AI features include a default AI feature of the third BWP. After the terminal device falls back to the third BWP, communication may be performed based on the default AI feature of the third BWP. Of course, in the embodiments of the present application, after the terminal device falls back to the third BWP, communication may be performed based on any one of the multiple AI features.

[0196] For example, if the second configuration information is used to configure a default AI feature for the third BWP, the terminal device communicating with the network device based on the second configuration information includes: the terminal device communicating with the network device based on the default AI feature in the third BWP configured by the second configuration information.

[0197] It should be noted that the first configuration information described above in conjunction with Embodiments 1 to 3 can be used alone or in combination. The following describes a solution in which Embodiments 1 to 3 are used in combination with each other in conjunction with FIG.

[0198] Figure 9 illustrates four BWPs applicable to embodiments of the present application. As shown in Figure 9 , assume that the network device has configured four BWPs for the terminal device: BWP1 through BWP4. BWP1 has a bandwidth of 20 MHz and an SCS of 30 kHz. BWP2 has a bandwidth of 50 MHz and an SCS of 30 kHz. BWP3 has a bandwidth of 50 MHz and an SCS of 120 kHz. BWP4 has a bandwidth of 100 MHz and an SCS of 120 kHz. Furthermore, the network device has configured each of the aforementioned BWPs, BWP1 through BWP4. The configuration corresponding to each BWP can be found in Table 1.

[0199] Table 1

[0200] As shown in Table 1, the first configuration information for BWP1 includes BWP1 configuration, AI function / AI feature configuration, model configuration supported for AI function / AI feature 1, model configuration supported for AI function / AI feature 2, and model configuration supported for AI function / AI feature 3. The BWP1 configuration configures the bandwidth of BWP1 to 20 MHz and the SCS of BWP1 to 30 kHz. The AI ​​function / AI feature configuration indicates that BWP1 supports AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3. The model configuration supported for AI function / AI feature 1 configures BWP1 with multiple models for implementing AI function / AI feature 1, including model 1-1 and model 1-2, with model 1-1 being the default model. The model configuration supported for AI function / AI feature 2 configures BWP1 with multiple models for implementing AI function / AI feature 2, including model 2-1, model 2-2, and model 2-3, with model 2-1 being the default model. The model configuration supported by the AI ​​function / AI feature 3 is used to configure multiple models for BWP1 to implement the AI ​​function / AI feature 3, including: model 3-1, model 3-2 and model 3-3, where model 3-1 is the default model.

[0201] The first configuration information for BWP2 includes BWP2 configuration, AI function / AI feature configuration, model configuration supported for AI function / AI feature 1, and model configuration supported for AI function / AI feature 2. The BWP2 configuration is used to configure the bandwidth of BWP2 to 50 MHz and the SCS of BWP2 to 30 kHz. The AI ​​function / AI feature configuration is used to indicate that BWP2 supports AI function / AI feature 1 and AI function / AI feature 2, but does not support AI function / AI feature 3. The model configuration supported for AI function / AI feature 1 is used to configure BWP2 with multiple models for implementing AI function / AI feature 1, including models 1-3 and 1-4, with model 1-3 being the default model. The model configuration supported for AI function / AI feature 2 is used to configure BWP2 with multiple models for implementing AI function / AI feature 2, including models 2-4, 2-5, and 2-6, with model 2-4 being the default model.

[0202] The first configuration information for BWP3 includes BWP3 configuration, AI function / AI feature configuration, supported model configuration for AI function / AI feature 1, and supported model configuration for AI function / AI feature 3. The BWP3 configuration is used to configure the BWP3 bandwidth to 50 MHz and the BWP3 SCS to 120 kHz. The AI ​​function / AI feature configuration indicates that BWP3 supports AI function / AI feature 1 and AI function / AI feature 3, but does not support AI function / AI feature 2. The supported model configuration for AI function / AI feature 1 configures BWP3 with multiple models for implementing AI function / AI feature 1, including models 1-5 and 1-6, with model 1-5 being the default model. The supported model configuration for AI function / AI feature 3 configures BWP3 with multiple models for implementing AI function / AI feature 1, including models 3-4, 3-5, and 3-6, with model 3-4 being the default model.

[0203] The first configuration information for BWP4 includes BWP4 configuration and AI function / AI feature configuration. The BWP4 configuration is used to configure the BWP4 bandwidth to 100 MHz and the SCS of BWP4 to 120 kHz. The AI ​​function / AI feature configuration is used to indicate that BWP4 does not support AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3.

[0204] Based on the first configuration information for the four BWPs shown in Table 1, it can be seen that for BWP1, since the bandwidth of BWP1 is smaller among the four BWPs, the complexity requirement for the AI ​​model is the lowest. Since the subcarrier spacing of BWP1 is small, the duration corresponding to the time domain symbol is large (that is, the duration available for model inference is relatively large), so the requirement for the model inference duration of the AI ​​model is relatively low. Accordingly, BWP1 supports more AI functions / AI features, that is, BWP1 supports AI functions / AI features including AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3.

[0205] For BWP2, since the bandwidth of BWP2 is larger than that of BWP1, the complexity requirement of the AI ​​model for BWP2 is relatively higher than that for BWP1. Since the subcarrier spacing of BWP2 is the same as that of BWP1, the duration corresponding to the time domain symbols in BWP2 and BWP1 is the same (that is, the duration that can be used for model inference is the same). Accordingly, BWP1 supports more AI functions / AI features than BWP2, that is, BWP2 supports AI functions / AI features including AI function / AI feature 1 and AI function / AI feature 2.

[0206] For BWP3, since the bandwidth of BWP3 is the same as that of BWP2, BWP3 and BWP2 have similar requirements for the complexity of the AI ​​model. Since the subcarrier spacing of BWP3 is larger than that of BWP2, the duration corresponding to the time domain symbols in BWP3 and the duration corresponding to the time domain symbols in BWP2 become shorter (that is, the duration that BWP3 can be used for model inference is reduced compared to the duration that BWP2 can be used for model inference). Therefore, BWP3 has higher requirements for the duration of model inference of the AI ​​model than BWP2. Accordingly, the AI ​​functions / AI features supported by BWP3 include AI function / AI feature 1 and AI function / AI feature 3.

[0207] For BWP4, since BWP4 has the largest bandwidth among the four BWPs, BWP4 has the highest requirements for the complexity of the AI ​​model. Since the subcarrier spacing of BWP4 is the same as that of BWP3, the duration corresponding to the time domain symbols in BWP4 is shorter than the duration corresponding to the time domain symbols in BWP2 (that is, the duration that BWP4 can be used for model inference is shorter than the duration that BWP2 can be used for model inference). Therefore, BWP4 has higher requirements for the duration of model inference of the AI ​​model than BWP2. Currently, AI Function / AI Feature 1 to AI Function / AI Feature 3 do not meet the relevant requirements of BWP4. Therefore, BWP4 does not support AI Function / AI Feature 1 to AI Function / AI Feature 3.

[0208] The above text introduces the first configuration information corresponding to BWP1 to BWP4 in an embodiment of the present application in combination with Figure 9. The following text takes BWP1 to BWP4 as an example and introduces the BWP switching process and the model fallback process in an embodiment of the present application in combination with Figures 10 to 14.

[0209] Figure 10 is a schematic diagram of the BWP switching process from BWP1 to BWP2 in an embodiment of the present application. As shown in Figure 10 , assuming that BWP1 is the default BWP, the terminal device communicates on BWP1 based on the first configuration information for BWP1. The network device sends indication information 1 to the terminal device to instruct the activation of BWP2. Accordingly, in response to indication information 1, the terminal device starts countdown timer 1 and, during the operation of countdown timer 1, communicates based on the first configuration information corresponding to BWP2. In other words, during the process of the terminal device switching from BWP1 to BWP2, AI function / AI feature 3 switches from supported to unsupported, while other AI functions / AI features remain unchanged.

[0210] Accordingly, if countdown timer 1 reaches 0, the terminal device can switch from BWP2 to BWP1. In response to the BWP switch, the terminal device switches from the first configuration information corresponding to BWP2 to the first configuration information corresponding to BWP1, and communicates based on the first configuration information corresponding to BWP1. In other words, during the process of the terminal device switching from BWP2 to BWP1, AI function / AI feature 3 switches from being supported to being supported, and other AI functions / AI features remain unchanged.

[0211] Figure 11 is a schematic diagram of a BWP switching process from BWP1 to BWP2 according to another embodiment of the present application. As shown in Figure 11 , assuming BWP1 is the default BWP, the terminal device communicates on BWP1 based on the first configuration information for BWP1. The network device sends indication information 1 to the terminal device to instruct it to activate BWP2. Accordingly, in response to indication information 2, the terminal device starts countdown timer 1 and, during the operation of countdown timer 1, communicates based on the first configuration information corresponding to BWP2. In other words, during the process of switching from BWP1 to BWP2, for AI function / AI feature 1, the terminal device switches from model 1-1 (i.e., the default model of BWP1) to model 1-3 (i.e., the default model of BWP2). For AI function / AI feature 2, the terminal device switches from model 2-1 (i.e., the default model of BWP1) to model 2-4 (i.e., the default model of BWP2). For AI function / AI feature 3, the terminal device switches from model 3-1 (i.e., the default model of BWP1) to not supporting the AI ​​function / AI feature.

[0212] Correspondingly, if countdown timer 1 is reduced to 0, the terminal device can switch from BWP2 to BWP1, and in response to the switching of BWP, the terminal device switches from the first configuration information corresponding to BWP2 to the first configuration information corresponding to BWP1, and communicates based on the first configuration information corresponding to BWP1. That is to say, in the process of the terminal device switching from BWP2 to BWP1, with respect to AI function / AI feature 1, the terminal device switches from model 1-3 (i.e., the default model of BWP2) to model 1-1 (i.e., the default model of BWP1). With respect to AI function / AI feature 2, the terminal device switches from model 2-4 (i.e., the default model of BWP2) to model 2-1 (i.e., the default model of BWP1). With respect to AI function / AI feature 3, the terminal device switches from not supporting the AI ​​function / AI feature to model 3-1 (i.e., the default model of BWP1).

[0213] Figure 12 is a schematic diagram of a BWP switching process from BWP2 to BWP1 according to another embodiment of the present application. Referring to Figure 12, it is assumed that the network device sends an indication message 1 to the terminal device to instruct the activation of BWP2. Accordingly, in response to the indication message 1, the terminal device starts countdown timer 1, and during the operation of countdown timer 1, communicates based on the first configuration information corresponding to BWP2. For AI function / AI feature 1, the terminal device communicates based on model 1-3 (i.e., the default model of BWP2). In addition, during the operation of countdown timer 1, the network device sends an indication message 2 to the terminal device to instruct the activation of model 1-4. Accordingly, in response to the indication message 2, the terminal device starts countdown timer 2, and during the operation of countdown timer 2, communicates based on model 1-4 on BWP2. If countdown timer 2 is reduced to 0, the terminal device switches from model 1-4 to model 1-3 for communication on BWP2.

[0214] Accordingly, if countdown timer 1 reaches 0, the terminal device may switch from BWP2 to BWP1. In response to the BWP switch, the terminal device switches from the first configuration information corresponding to BWP2 to the first configuration information corresponding to BWP1, and communicates based on the first configuration information corresponding to BWP1. In other words, during the process of switching from BWP2 to BWP1, with respect to AI function / AI feature 1, the terminal device switches from model 1-3 (i.e., the default model for BWP2) to model 1-1 (i.e., the default model for BWP1).

[0215] Figure 13 is a schematic diagram of a BWP switching process from BWP2 to BWP1 according to another embodiment of the present application. Referring to Figure 13, it is assumed that the network device sends indication information 1 to the terminal device to instruct the activation of BWP2. Accordingly, in response to indication information 1, the terminal device starts countdown timer 1, and during the operation of countdown timer 1, communicates based on the first configuration information corresponding to BWP2. For AI function / AI feature 1, the terminal device communicates based on model 1-3 (i.e., the default model of BWP2). In addition, during the operation of countdown timer 1, the network device sends indication information 2 to the terminal device to instruct the activation of model 1-4. Accordingly, in response to indication information 2, the terminal device starts countdown timer 2, and during the operation of countdown timer 2, communicates based on model 1-4 on BWP2. If countdown timer 1 is reduced to 0 before countdown timer 2 is reduced to 0, then in response to countdown timer 1 being reduced to 0, the terminal device switches from BWP2 to BWP1. Accordingly, the terminal device switches from the first configuration information corresponding to BWP2 to the first configuration information corresponding to BWP1, that is, the terminal device switches from model 1-4 to model 1-1 (that is, the default model of BWP1).

[0216] With the widespread adoption of communication systems, various types of terminal devices have been introduced. Each type of terminal device may support different AI / ML-related capabilities. Currently, network devices are typically configured uniformly at the BWP granularity. However, this BWP-based unified configuration approach may render some terminal devices that operate within the BWP inoperable, reducing the accuracy of network device configuration.

[0217] Therefore, in response to the above problems, an embodiment of the present application also provides a method for transmitting capability information, in which the terminal device can send capability information associated with the first BWP to the network device, so that the network device can perform configuration associated with AI / ML for the terminal device based on the capability information (for example, the first configuration information mentioned above), which helps to improve the accuracy of the network device configuration.

[0218] In some implementations, the capability information is used to indicate one or more of the following: models supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; and AI features supported by the terminal device and available for the first BWP.

[0219] Taking the capability information as an example, which indicates the models supported by the terminal device and can be used for the first BWP, in some implementations, the capability information can carry the model identifiers of one or more models, which helps reduce the overhead of transmitting the capability information. Of course, in the embodiment of the present application, the capability information can directly carry the one or more models themselves.

[0220] In some implementations, the capability information is used to indicate one or more models supported by the terminal device that can be used for the first BWP and for implementing the first AI function. In other implementations, the capability information is used to indicate one or more models supported by the terminal device that can be used for the first BWP and for implementing the first AI feature.

[0221] In the embodiments of the present application, there is no limitation on the manner in which the capability information indicates one or more models. For example, the capability information may carry the model identifiers of one or more models, which helps reduce the overhead of transmitting the capability information. Of course, in the embodiments of the present application, the capability information may directly carry the one or more models themselves.

[0222] In some implementations, the capability information indicates a default model among the models supported by the terminal device and available for the first BWP. The default model is activated in response to the first BWP being activated. It should be understood that the default model is described above and will not be further described here for the sake of brevity. Of course, in embodiments of the present application, the capability information may not indicate a default model.

[0223] Take the example of capability information being used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, or in other words, the capability information is used to indicate whether the terminal device supports AI-based processing for a certain function in the first BWP.

[0224] In some implementations, the AI ​​function that can be used for the first BWP includes one or more AI functions, and the introduction of the AI ​​functions can be found in the previous introduction. For the sake of brevity, they will not be repeated here.

[0225] In some implementations, the capability information includes AI function identifiers of one or more AI functions to reduce the overhead of transmitting the capability information.

[0226] In some implementations, the capability information indicates a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP. Activation of the default AI function is responsive to activation of the first BWP. It should be understood that the default AI function is described above and will not be further described here for the sake of brevity. Of course, in embodiments of the present application, the capability information may not indicate the default AI function.

[0227] For example, the capability information is used to indicate the AI ​​features supported by the terminal device and available for the first BWP. In other words, the capability information is used to indicate whether the terminal device supports AI-based processing for a certain feature in the first BWP.

[0228] In some implementations, the AI ​​features that can be used for the first BWP include one or more AI features. For an introduction to the AI ​​features, please refer to the above description, which will not be repeated here for the sake of brevity.

[0229] In some implementations, the capability information includes AI feature identifiers of one or more AI features to reduce the overhead of transmitting the capability information.

[0230] In some implementations, the capability information indicates a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP. The activation of the default AI feature is responsive to the activation of the first BWP. It should be understood that the default AI feature can be found in the above description and will not be further described here for the sake of brevity. Of course, in embodiments of the present application, the capability information may not indicate the default AI feature.

[0231] It should be noted that, in the embodiment of the present application, the capability information may also include identification information of the first BWP so that the network device can determine which BWP the capability information is associated with. Of course, in some scenarios, the capability information may not include identification information of the first BWP.

[0232] For ease of understanding, the following continues to introduce the four types of BWPs shown in Figure 9 as an example. Accordingly, the capability information of the terminal device for each BWP can be found in Table 2.

[0233] Table 2

[0234] As shown in Table 2, the capability information for BWP1 includes information on supported AI functions / AI features, information on models supported for AI function / AI feature 1, models supported for AI function / AI feature 2, and models supported for AI function / AI feature 3. The information on supported AI functions / AI features indicates that the AI ​​functions / AI features supported by the terminal device on BWP1 include: AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3. The information on supported models for AI function / AI feature 1 indicates that the terminal device supports multiple models for implementing AI function / AI feature 1 on BWP1, including model 1-1 and model 1-2, with model 1-1 being the default model. The information on supported models for AI function / AI feature 2 indicates that the terminal device supports multiple models for implementing AI function / AI feature 2 on BWP1, including model 2-1, model 2-2, and model 2-3, with model 2-1 being the default model. The information on the models supported by the AI ​​function / AI feature 3 is used to indicate that the terminal device supports multiple models for implementing the AI ​​function / AI feature 3 on BWP1, including: model 3-1, model 3-2 and model 3-3, where model 3-1 is the default model.

[0235] The capability information for BWP2 includes information on supported AI functions / AI features, information on models supported for AI function / AI feature 1, and models supported for AI function / AI feature 2. The information on supported AI functions / AI features is used to indicate that the terminal device supports AI function / AI feature 1 and AI function / AI feature 2 on BWP2, but does not support AI function / AI feature 3. The information on models supported for AI function / AI feature 1 is used to indicate that the terminal device supports multiple models for implementing AI function / AI feature 1 on BWP2, including models 1-3 and 1-4, where model 1-3 is the default model. The information on models supported for AI function / AI feature 2 is used to indicate that the terminal device supports multiple models for implementing AI function / AI feature 2 on BWP2, including models 2-4, 2-5, and 2-6, where model 2-4 is the default model.

[0236] The capability information for BWP3 includes information about supported AI functions / AI features, information about supported models for AI function / AI feature 1, and information about supported models for AI function / AI feature 3. The information about supported AI functions / AI features indicates that the terminal device on BWP3 supports AI function / AI feature 1 and AI function / AI feature 3, but does not support AI function / AI feature 2. The model configuration supported for AI function / AI feature 1 is used to configure BWP3 with multiple models for implementing AI function / AI feature 1: models 1-5 and 1-6, with model 1-5 being the default model. The model configuration supported for AI function / AI feature 3 is used to configure BWP3 with multiple models for implementing AI function / AI feature 1: models 3-4, 3-5, and 3-6, with model 3-4 being the default model.

[0237] The capability information for BWP4 includes information on supported AI functions / AI features, where the information on supported AI functions / AI features indicates that the terminal device does not support AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3 on BWP4.

[0238] Based on the capability information for the four BWPs shown in Table 2, it can be seen that for BWP1, since the bandwidth of BWP1 is smaller among the four BWPs, the complexity requirement for the AI ​​model is the lowest. Since the subcarrier spacing of BWP1 is small, the duration corresponding to the time domain symbol is large (that is, the duration available for model inference is relatively large), so the requirement for the model inference duration of the AI ​​model is relatively low. Accordingly, the terminal device supports more AI functions / AI features on BWP1, that is, BWP1 supports AI functions / AI features including AI function / AI feature 1, AI function / AI feature 2, and AI function / AI feature 3.

[0239] For BWP2, since the bandwidth of BWP2 is larger than that of BWP1, the complexity requirement of the AI ​​model for BWP2 is relatively higher than that for BWP1. Since the subcarrier spacing of BWP2 is the same as that of BWP1, the duration corresponding to the time domain symbols in BWP2 and BWP1 is the same (that is, the duration that can be used for model inference is the same). Accordingly, the terminal device supports more AI functions / AI features on BWP1 than on BWP2, that is, the terminal device supports more AI functions / AI features on BWP2, that is, the AI ​​functions / AI features supported by the terminal device on BWP2 include AI function / AI feature 1 and AI function / AI feature 2.

[0240] For BWP3, since the bandwidth of BWP3 is the same as that of BWP2, BWP3 and BWP2 have similar requirements for the complexity of the AI ​​model. Since the subcarrier spacing of BWP3 is larger than that of BWP2, the duration corresponding to the time domain symbols in BWP3 and the duration corresponding to the time domain symbols in BWP2 become shorter (that is, the duration that BWP3 can be used for model inference is shorter than the duration that BWP2 can be used for model inference). Therefore, BWP3 has higher requirements for the duration of model inference of the AI ​​model than BWP2. Accordingly, the AI ​​functions / AI features supported by the terminal device on BWP3 include AI function / AI feature 1 and AI function / AI feature 3.

[0241] For BWP4, since BWP4 has the largest bandwidth among the four BWPs, BWP4 has the highest requirements for the complexity of the AI ​​model. Since the subcarrier spacing of BWP4 is the same as that of BWP3, the duration corresponding to the time domain symbols in BWP4 is shorter than the duration corresponding to the time domain symbols in BWP2 (that is, the duration that BWP4 can be used for model inference is shorter than the duration that BWP2 can be used for model inference). Therefore, BWP4 has higher requirements for the model inference duration of the AI ​​model than BWP2. Currently, terminal devices do not support AI function / AI feature 1 to AI function / AI feature 3 on BWP4.

[0242] In an embodiment of the present application, the capability information involved above can be carried by one or more of the following message types: NR Positioning Protocol A (NRPPa) message, long term evolution positioning protocol (LPP) message, non-access stratum (NAS) message, radio resource control (RRC) message, media access control control element (MAC CE), downlink control information (DCI), uplink control information (UCI), physical uplink control channel (PUCCH), physical uplink shared channel (PUSCH), inter-node message, Xn interface message, F1 interface message, E1 interface message, NG interface message, core network service architecture-based message or AI dedicated message.

[0243] In an embodiment of the present application, the capability information mentioned above can be carried by one or more of unicast messages, multicast messages and broadcast messages.

[0244] Unicast messages can be understood as one-to-one transmissions, meaning they are sent from one sender to one receiver. The source delivers unicast messages over a unicast channel, and only devices or network equipment allocated the corresponding unicast resources can attempt to receive them. Unicast messages are also called dedicated signaling.

[0245] The multicast message described above can be understood as a one-to-many transmission, meaning it's sent from a single sender to multiple receivers. The source transmits the message via a multicast channel. Terminal devices or network devices within the multicast signal's coverage area and that are members of the group can attempt to receive the message. When a terminal device or network device joins a group, it acquires multicast channel resources.

[0246] The broadcast message can be understood as a message transmitted from one sender to any receiver. The source transmits the message via a broadcast channel, and any terminal or network device within the coverage area of ​​the broadcast signal can attempt to receive it.

[0247] The method embodiment of the present application is described in detail above in conjunction with Figures 1 to 13. The device embodiment of the present application is described in detail below in conjunction with Figures 14 to 16. It should be understood that the description of the method embodiment corresponds to the description of the device embodiment. Therefore, for parts not described in detail, reference can be made to the above method embodiment.

[0248] FIG14 is a schematic diagram of a terminal device according to an embodiment of the present application. The terminal device 1400 shown in FIG14 includes: a receiving unit 1410 .

[0249] The receiving unit 1410 is used to receive first configuration information sent by the network device, where the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: a first model; a first artificial intelligence AI function; or a first AI feature.

[0250] In some implementations, the first configuration information is used to configure one or more models that implement a first AI function, where the one or more models include the first model.

[0251] In some implementations, the first configuration information includes model identifications of the one or more models.

[0252] In some implementations, the first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

[0253] In some implementations, the first configuration information is used to indicate the first default model among the multiple models, and the receiving unit is further used to receive first indication information sent by the network device, and the first indication information is used to indicate the activation of other models among the multiple models except the first default model.

[0254] In some implementations, the terminal device further includes a first processing unit configured to: start a first timer in response to receiving the first indication information; and communicate with the network device based on the other model during the operation of the first timer.

[0255] In some implementations, the first processing unit is configured to: in response to expiration of the first timer, communicate with the network device based on the first default model.

[0256] In some implementations, the first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

[0257] In some implementations, the first configuration information includes AI function identifiers of the one or more AI functions.

[0258] In some implementations, the first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

[0259] In some implementations, the first configuration information is used to indicate the first default AI function among the multiple AI functions, and the receiving unit is further used to: receive second indication information sent by the network device, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

[0260] In some implementations, the terminal device further includes a second processing unit, which is configured to: start a second timer in response to receiving the second indication information; and communicate with the network device based on the other AI functions during the operation of the second timer.

[0261] In some implementations, the second processing unit is configured to: in response to expiration of the second timer, communicate with the network device based on the first default AI function.

[0262] In some implementations, the first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

[0263] In some implementations, the first configuration information includes AI feature identifiers of the one or more AI features.

[0264] In some implementations, the first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

[0265] In some implementations, the first configuration information is used to indicate the first default AI function among the multiple AI functions, and the receiving unit is further used to: receive third indication information sent by the network device, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

[0266] In some implementations, the terminal device further includes a third processing unit, which is configured to: start a third timer in response to receiving the third indication information; and communicate with the network device based on the other AI characteristics during the operation of the third timer.

[0267] In some implementations, the third processing unit is configured to: in response to expiration of the third timer, communicate with the network device based on the first default AI feature.

[0268] In some implementations, the terminal device further includes a fourth processing unit, and the fourth processing unit is further configured to: in response to activating the first BWP, communicate with the network device based on the first configuration information.

[0269] In some implementations, activating the first BWP includes switching the terminal device from a second BWP to the first BWP, where the second BWP is different from the first BWP.

[0270] In some implementations, the fourth processing unit is further configured to: start a fourth timer in response to activating the first BWP; and communicate with the network device based on the first configuration information while the fourth timer is running.

[0271] In some implementations, the fourth processing unit is further used to: in response to the fourth timer expiring, communicate with the network device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI characteristic.

[0272] In some implementations, the third BWP is a default BWP.

[0273] In some implementations, the terminal device communicates with the network device based on the second configuration information, including one of the following: the terminal device communicates with the network device based on the default model in the third BWP configured by the second configuration information; the terminal device communicates with the network device based on the default AI function in the third BWP configured by the second configuration information; the terminal device communicates with the network device based on the default AI feature in the third BWP configured by the second configuration information.

[0274] In some implementations, the first configuration information includes one or more of the following: the first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP; and the parameter set of the first BWP.

[0275] In some implementations, the terminal device further includes a sending unit, which is used to send capability information to the network device, where the capability information is used to indicate one or more of the following: models supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; and AI features supported by the terminal device and available for the first BWP.

[0276] In some implementations, the capability information is used to indicate the models supported by the terminal device that can be used for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device that can be used for the first BWP and are used to implement the first AI function.

[0277] In some implementations, the capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes model identifiers of the models supported by the terminal device and available for use in the first BWP.

[0278] In some implementations, the capability information is used to indicate a default model among models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

[0279] In some implementations, the capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

[0280] In some implementations, the capability information includes AI function identifiers of the one or more AI functions.

[0281] In some implementations, the capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

[0282] In some implementations, the capability information is used to indicate AI features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

[0283] In some implementations, the capability information includes AI feature identifiers of the one or more AI features.

[0284] In some implementations, the capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

[0285] FIG15 is a schematic diagram of a network device according to an embodiment of the present application. The network device 1500 shown in FIG15 includes: a sending unit 1510 .

[0286] The sending unit 1510 is used to send first configuration information to the terminal device, where the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: a first model; a first artificial intelligence AI function; a first AI feature.

[0287] In some implementations, the first configuration information is used to configure one or more models that implement a first AI function, where the one or more models include the first model.

[0288] In some implementations, the first configuration information includes model identifications of the one or more models.

[0289] In some implementations, the first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

[0290] In some implementations, the first configuration information is used to indicate the first default model among the multiple models, and the sending unit is used to: send first indication information to the terminal device, where the first indication information is used to indicate activation of other models among the multiple models except the first default model.

[0291] In some implementations, the network device further includes a first processing unit, which is configured to: start a first timer in response to sending the first indication information; and communicate with the terminal device based on the other model during the operation of the first timer.

[0292] In some implementations, the first processing unit is configured to: in response to expiration of the first timer, communicate with the terminal device based on the first default model.

[0293] In some implementations, the first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

[0294] In some implementations, the first configuration information includes AI function identifiers of the one or more AI functions.

[0295] In some implementations, the first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

[0296] In some implementations, the first configuration information is used to indicate the first default AI function among the multiple AI functions, and the sending unit is used to send second indication information to the terminal device, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

[0297] In some implementations, the network device further includes a second processing unit, which is configured to start a second timer in response to sending the second indication information; and communicate with the terminal device based on the other AI functions during the operation of the second timer.

[0298] In some implementations, the second processing unit is configured to communicate with the terminal device based on the first default AI function in response to expiration of the second timer.

[0299] In some implementations, the first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

[0300] In some implementations, the first configuration information includes AI feature identifiers of the one or more AI features.

[0301] In some implementations, the first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

[0302] In some implementations, the first configuration information is used to indicate the first default AI feature among the multiple AI features, and the sending unit is further used to: send third indication information to the terminal device, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

[0303] In some implementations, the network device further includes a third processing unit, configured to: start a third timer in response to sending the third indication information; and communicate with the terminal device based on the other AI characteristics during the operation of the third timer.

[0304] In some implementations, the third processing unit is configured to: in response to expiration of the third timer, communicate with the terminal device based on the first default AI feature.

[0305] In some implementations, the network device further includes a fourth processing unit, configured to: in response to activating the first BWP, communicate with the terminal device based on the first configuration information.

[0306] In some implementations, activating the first BWP includes switching the terminal device from a second BWP to the first BWP, where the second BWP is different from the first BWP.

[0307] In some implementations, the fourth processing unit is configured to: start a fourth timer in response to activating the first BWP; and communicate with the terminal device based on the first configuration information during the running of the fourth timer.

[0308] In some implementations, the fourth processing unit is used to: in response to the fourth timer expiring, communicate with the terminal device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI characteristic.

[0309] In some implementations, the third BWP is a default BWP.

[0310] In some implementations, the network device communicates with the terminal device based on the second configuration information, including one of the following: the network device communicates with the terminal device based on the default model in the third BWP configured by the second configuration information; the network device communicates with the terminal device based on the default AI function in the third BWP configured by the second configuration information; the network device communicates with the terminal device based on the default AI feature in the third BWP configured by the second configuration information.

[0311] In some implementations, the first configuration information includes one or more of the following: the first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP; and the parameter set of the first BWP.

[0312] In some implementations, the network device further includes: a receiving unit for receiving capability information sent by the terminal device, where the capability information is used to indicate one or more of the following: a model supported by the terminal device and available for the first BWP; an AI function supported by the terminal device and available for the first BWP; and an AI feature supported by the terminal device and available for the first BWP.

[0313] In some implementations, the capability information is used to indicate the models supported by the terminal device that can be used for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device that can be used for the first BWP and are used to implement the first AI function.

[0314] In some implementations, the capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes model identifiers of the models supported by the terminal device and available for use in the first BWP.

[0315] In some implementations, the capability information is used to indicate a default model among models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

[0316] In some implementations, the capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

[0317] In some implementations, the capability information includes AI function identifiers of the one or more AI functions.

[0318] In some implementations, the capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

[0319] In some implementations, the capability information is used to indicate AI features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

[0320] In some implementations, the capability information includes AI feature identifiers of the one or more AI features.

[0321] In some implementations, the capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

[0322] In an optional embodiment, the receiving unit 1410 may be a transceiver 1630. The terminal device 1400 may further include a processor 1610 and a memory 1620, as specifically shown in FIG16 .

[0323] In an optional embodiment, the sending unit 1510 may be a transceiver 1630. The network device 1500 may further include a processor 1610 and a memory 1620, as specifically shown in FIG16 .

[0324] Figure 16 is a schematic block diagram of a communication device according to an embodiment of the present application. The dashed lines in Figure 16 indicate that the unit or module is optional. Device 1600 may be used to implement the method described in the above method embodiment. Device 1600 may be a chip, a terminal device, or a network device.

[0325] The device 1600 may include one or more processors 1610. The processor 1610 may support the device 1600 to implement the method described in the above method embodiment. The processor 1610 may be a general-purpose processor or a special-purpose processor. For example, the processor may be a central processing unit (CPU). Alternatively, the processor may be another general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0326] The apparatus 1600 may further include one or more memories 1620. The memories 1620 store programs that can be executed by the processor 1610, causing the processor 1610 to perform the methods described in the above method embodiments. The memories 1620 may be independent of the processor 1610 or integrated into the processor 1610.

[0327] The apparatus 1600 may further include a transceiver 1630. The processor 1610 may communicate with other devices or chips via the transceiver 1630. For example, the processor 1610 may transmit and receive data with other devices or chips via the transceiver 1630.

[0328] The present application also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal or network device provided in the present application, and the program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0329] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to a terminal or network device provided in the present application, and the program causes a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0330] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal or network device provided in the embodiments of the present application, and the computer program enables a computer to execute the method performed by the terminal or network device in each embodiment of the present application.

[0331] It should be understood that the terms "system" and "network" in this application can be used interchangeably. In addition, the terms used in this application are only used to explain the specific embodiments of this application and are not intended to limit this application. The terms "first", "second", "third", and "fourth" in the specification and claims of this application and the accompanying drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions.

[0332] In the embodiments of this application, the term "indication" may refer to a direct indication, an indirect indication, or an indication of an association. For example, "A indicates B" may refer to a direct indication of B, e.g., B can obtain information through A; it may refer to an indirect indication of B, e.g., A indicates C, e.g., B can obtain information through C; or it may refer to an association between A and B.

[0333] In the embodiment of the present application, "B corresponding to A" means that B is associated with A and B can be determined based on A. However, it should be understood that determining B based on A does not mean determining B based solely on A, but B can also be determined based on A and / or other information.

[0334] In the embodiments of the present application, the term "corresponding" may indicate a direct or indirect correspondence between the two, or an association relationship between the two, or a relationship between indication and indication, configuration and configuration, etc.

[0335] In the embodiments of the present application, "pre-definition" or "pre-configuration" may be implemented by pre-storing corresponding codes, tables, or other methods that can be used to indicate relevant information in a device (e.g., a terminal device and a network device). The present application does not limit the specific implementation method. For example, pre-definition may refer to information defined in a protocol.

[0336] In the embodiments of the present application, the “protocol” may refer to a standard protocol in the communications field, for example, it may include an LTE protocol, an NR protocol, and related protocols used in future communication systems, and the present application does not limit this.

[0337] In the embodiments of this application, the term "and / or" is simply a description of the association relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0338] In various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0339] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0340] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0341] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0342] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be read by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital versatile disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0343] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for transmitting configuration information, characterized in that: include: The terminal device receives first configuration information sent by the network device, where the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: First model; First artificial intelligence AI function; First AI feature.

2. The method according to claim 1, characterized in that The first configuration information is used to configure the first model for the first BWP, and the first configuration information is used to configure one or more models that implement a first AI function, and the one or more models include the first model.

3. The method according to claim 2, characterized in that The first configuration information includes model identifications of the one or more models.

4. The method according to claim 2 or 3, characterized in that The first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

5. The method according to claim 4, characterized in that The method further comprises: The terminal device receives first indication information sent by the network device, where the first indication information is used to indicate activation of other models among the multiple models except the first default model.

6. The method according to claim 5, characterized in that The method further comprises: In response to receiving the first indication information, the terminal device starts a first timer; While the first timer is running, the terminal device communicates with the network device based on the other model.

7. The method according to claim 6, characterized in that The method further comprises: In response to the first timer expiring, the terminal device communicates with the network device based on the first default model.

8. The method according to any one of claims 1 to 7, characterized in that The first configuration information is used to configure the first AI function for the first BWP, and the first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

9. The method according to claim 8, characterized in that The first configuration information includes AI function identifiers of the one or more AI functions.

10. The method according to claim 8 or 9, characterized in that The first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

11. The method according to any one of claims 8 to 10, characterized in that The method further comprises: The terminal device receives second indication information sent by the network device, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

12. The method according to claim 11, characterized in that The method further comprises: In response to receiving the second indication information, the terminal device starts a second timer; While the second timer is running, the terminal device communicates with the network device based on the other AI functions.

13. The method according to claim 12, characterized in that The method further comprises: In response to the second timer timing out, the terminal device communicates with the network device based on the first default AI function.

14. The method according to any one of claims 1 to 13, characterized in that The first configuration information is used to configure the first AI feature for the first BWP, and the first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

15. The method according to claim 14, characterized in that The first configuration information includes AI feature identifiers of the one or more AI features.

16. The method according to claim 13 or 14, characterized in that The first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

17. The method according to any one of claims 14 to 16, characterized in that The method further comprises: The terminal device receives third indication information sent by the network device, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

18. The method according to claim 17, characterized in that The method further comprises: In response to receiving the third indication information, the terminal device starts a third timer; While the third timer is running, the terminal device communicates with the network device based on the other AI characteristics.

19. The method according to claim 18, characterized in that The method further comprises: In response to the third timer expiring, the terminal device communicates with the network device based on the first default AI characteristic.

20. The method according to any one of claims 1 to 19, characterized in that The method further comprises: In response to activating the first BWP, the terminal device communicates with the network device based on the first configuration information.

21. The method of claim 20, wherein: The activating the first BWP includes the terminal device switching from a second BWP to the first BWP, where the second BWP is different from the first BWP.

22. The method according to claim 20 or 21, characterized in that The method further comprises: In response to activating the first BWP, the terminal device starts a fourth timer; While the fourth timer is running, the terminal device communicates with the network device based on the first configuration information.

23. The method of claim 22, wherein: The method further comprises: In response to the fourth timer timing out, the terminal device communicates with the network device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI characteristic.

24. The method of claim 23, wherein: The third BWP is the default BWP.

25. The method according to claim 23 or 24, characterized in that The terminal device communicating with the network device based on the second configuration information includes one of the following: The terminal device communicates with the network device based on a default model in the third BWP configured by the second configuration information; The terminal device communicates with the network device based on the default AI function in the third BWP configured by the second configuration information; The terminal device communicates with the network device based on the default AI characteristics in the third BWP configured by the second configuration information.

26. The method according to any one of claims 1 to 25, characterized in that The first configuration information includes one or more of the following: The first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP and the parameter set of the first BWP.

27. The method according to any one of claims 1 to 26, characterized in that The method further comprises: The terminal device sends capability information to the network device, where the capability information is used to indicate one or more of the following: A model supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; The terminal device supports AI features that can be used for the first BWP.

28. The method of claim 27, wherein: The capability information is used to indicate the models supported by the terminal device and available for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device and available for the first BWP and used to implement the first AI function.

29. The method according to claim 27 or 28, characterized in that The capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes the model identifier of the model supported by the terminal device and available for use in the first BWP.

30. The method according to claim 28 or 29, characterized in that The capability information is used to indicate a default model among the models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

31. The method according to any one of claims 27 to 30, characterized in that The capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

32. The method of claim 31, wherein: The capability information includes AI function identifiers of the one or more AI functions.

33. The method according to claim 31 or 32, characterized in that The capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

34. The method according to any one of claims 27 to 33, characterized in that The capability information is used to indicate the AI ​​features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

35. The method of claim 34, wherein: The capability information includes AI feature identifiers of the one or more AI features.

36. The method according to claim 34 or 35, characterized in that The capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

37. A method for transmitting configuration information, characterized in that: include: The network device sends first configuration information to the terminal device, where the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: First model; First artificial intelligence AI function; First AI feature.

38. The method of claim 37, wherein The first configuration information is used to configure one or more models that implement a first AI function, and the one or more models include the first model.

39. The method of claim 38, wherein: The first configuration information includes model identifications of the one or more models.

40. The method according to claim 38 or 39, characterized in that The first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

41. The method of claim 40, wherein: The first configuration information is used to indicate the first default model among the multiple models, and the method further includes: The network device sends first indication information to the terminal device, where the first indication information is used to indicate activation of other models among the multiple models except the first default model.

42. The method of claim 41, wherein: The method further comprises: In response to sending the first indication information, the network device starts a first timer; While the first timer is running, the network device communicates with the terminal device based on the other model.

43. The method of claim 42, wherein: The method further comprises: In response to the first timer expiring, the network device communicates with the terminal device based on the first default model.

44. The method according to any one of claims 37 to 43, characterized in that The first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

45. The method of claim 44, wherein: The first configuration information includes AI function identifiers of the one or more AI functions.

46. ​​The method according to claim 44 or 45, characterized in that The first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

47. The method according to any one of claims 44 to 46, characterized in that The first configuration information is used to indicate the first default AI function among the multiple AI functions, and the method further includes: The network device sends second indication information to the terminal device, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

48. The method of claim 47, wherein: The method further comprises: In response to sending the second indication information, the network device starts a second timer; While the second timer is running, the network device communicates with the terminal device based on the other AI function.

49. The method of claim 48, wherein: The method further comprises: In response to the second timer expiring, the network device communicates with the terminal device based on the first default AI function.

50. The method according to any one of claims 37 to 49, characterized in that The first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

51. The method of claim 50, wherein: The first configuration information includes AI feature identifiers of the one or more AI features.

52. The method of claim 49 or 50, wherein: The first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

53. The method according to any one of claims 50 to 52, characterized in that The first configuration information is used to indicate the first default AI feature among the multiple AI features, and the method further includes: The network device sends third indication information to the terminal device, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

54. The method of claim 53, wherein: The method further comprises: In response to sending the third indication information, the network device starts a third timer; While the third timer is running, the network device communicates with the terminal device based on the other AI characteristics.

55. The method of claim 54, wherein: The method further comprises: In response to the third timer expiring, the network device communicates with the terminal device based on the first default AI characteristic.

56. The method according to any one of claims 37 to 55, characterized in that The method further comprises: In response to activating the first BWP, the network device communicates with the terminal device based on the first configuration information.

57. The method of claim 56, wherein: The activating the first BWP includes the terminal device switching from a second BWP to the first BWP, where the second BWP is different from the first BWP.

58. The method of claim 56 or 57, wherein: The method further comprises: In response to activating the first BWP, the network device starts a fourth timer; While the fourth timer is running, the network device communicates with the terminal device based on the first configuration information.

59. The method of claim 58, wherein: The method further comprises: In response to the fourth timer timing out, the network device communicates with the terminal device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI characteristic.

60. The method of claim 59, wherein: The third BWP is the default BWP.

61. The method of claim 59 or 60, wherein: The network device communicating with the terminal device based on the second configuration information includes one of the following: The network device communicates with the terminal device based on a default model in the third BWP configured by the second configuration information; The network device communicates with the terminal device based on the default AI function in the third BWP configured by the second configuration information; The network device communicates with the terminal device based on the default AI characteristics in the third BWP configured by the second configuration information.

62. The method according to any one of claims 37 to 61, wherein: The first configuration information includes one or more of the following: The first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP and the parameter set of the first BWP.

63. The method according to any one of claims 37 to 62, characterized in that The method further comprises: The network device receives capability information sent by the terminal device, where the capability information is used to indicate one or more of the following: A model supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; The terminal device supports AI features that can be used for the first BWP.

64. The method of claim 63, wherein: The capability information is used to indicate the models supported by the terminal device and available for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device and available for the first BWP and used to implement the first AI function.

65. The method of claim 63 or 64, wherein: The capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes the model identifier of the model supported by the terminal device and available for use in the first BWP.

66. The method of claim 64 or 65, wherein: The capability information is used to indicate a default model among the models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

67. The method according to any one of claims 63 to 66, characterized in that The capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

68. The method of claim 67, wherein: The capability information includes AI function identifiers of the one or more AI functions.

69. The method of claim 67 or 68, wherein: The capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

70. The method according to any one of claims 63 to 69, characterized in that The capability information is used to indicate the AI ​​features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

71. The method of claim 70, wherein: The capability information includes AI feature identifiers of the one or more AI features.

72. The method of claim 70 or 71, wherein: The capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

73. A terminal device, characterized in that: include: A receiving unit, configured to receive first configuration information sent by a network device, wherein the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: First model; First artificial intelligence AI function; First AI feature.

74. The terminal device according to claim 73, characterized in that: The first configuration information is used to configure one or more models that implement a first AI function, and the one or more models include the first model.

75. The terminal device according to claim 74, characterized in that: The first configuration information includes model identifications of the one or more models.

76. The terminal device according to claim 74 or 75, characterized in that: The first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

77. The terminal device according to claim 76, characterized in that: The first configuration information is used to indicate the first default model among the multiple models, The receiving unit is further used to receive first indication information sent by the network device, where the first indication information is used to indicate activation of other models among the multiple models except the first default model.

78. The terminal device according to claim 77, characterized in that: The terminal device further includes a first processing unit, wherein the first processing unit is configured to: In response to receiving the first indication information, starting a first timer; and While the first timer is running, communicating with the network device is performed based on the other model.

79. The terminal device according to claim 78, characterized in that The first processing unit is used for: In response to the first timer expiring, communicating with the network device based on the first default model.

80. The terminal device according to any one of claims 73 to 79, characterized in that: The first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

81. The terminal device as claimed in claim 80, characterized in that: The first configuration information includes AI function identifiers of the one or more AI functions.

82. The terminal device according to claim 80 or 81, characterized in that: The first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

83. The terminal device according to any one of claims 80 to 82, characterized in that: The first configuration information is used to indicate the first default AI function among the multiple AI functions, and the receiving unit is further used to: Second indication information sent by the network device is received, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

84. The terminal device as claimed in claim 83, characterized in that: The terminal device further includes a second processing unit, wherein the second processing unit is configured to: In response to receiving the second indication information, starting a second timer; and While the second timer is running, communicating with the network device based on the other AI function.

85. The terminal device as claimed in claim 84, characterized in that: The second processing unit is used for: In response to the second timer expiring, communicating with the network device based on the first default AI function.

86. The terminal device according to any one of claims 73 to 85, characterized in that: The first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

87. The terminal device according to claim 86, characterized in that: The first configuration information includes AI feature identifiers of the one or more AI features.

88. The terminal device according to claim 85 or 86, characterized in that: The first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

89. The terminal device according to any one of claims 86 to 88, characterized in that: The first configuration information is used to indicate the first default AI function among the multiple AI functions, and the receiving unit is further used to: Third indication information sent by the network device is received, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

90. The terminal device as claimed in claim 89, characterized in that: The terminal device further includes a third processing unit, and the third processing unit is configured to: In response to receiving the third indication information, starting a third timer; During the execution of the third timer, communicating with the network device based on the other AI characteristics.

91. The terminal device according to claim 90, characterized in that: The third processing unit is used for: In response to the third timer expiring, communicating with the network device based on the first default AI characteristic.

92. The terminal device according to any one of claims 73 to 91, characterized in that: The terminal device further includes a fourth processing unit, and the fourth processing unit is further configured to: In response to activating the first BWP, communicating with the network device based on the first configuration information.

93. The terminal device as claimed in claim 92, characterized in that: The activating the first BWP includes the terminal device switching from a second BWP to the first BWP, where the second BWP is different from the first BWP.

94. The terminal device according to claim 92 or 93, characterized in that: The fourth processing unit is further configured to: In response to activating the first BWP, starting a fourth timer; During the running of the fourth timer, communicating with the network device based on the first configuration information.

95. The terminal device according to claim 94, characterized in that: The fourth processing unit is further configured to: In response to the fourth timer expiring, communicating with the network device based on second configuration information, wherein the second configuration information is used to The three BWPs configure one or more of the following: a second model; a second AI function; and a second AI characteristic.

96. The terminal device as claimed in claim 95, characterized in that: The third BWP is the default BWP.

97. The terminal device according to claim 95 or 96, characterized in that: The terminal device communicating with the network device based on the second configuration information includes one of the following: The terminal device communicates with the network device based on a default model in the third BWP configured by the second configuration information; The terminal device communicates with the network device based on the default AI function in the third BWP configured by the second configuration information; The terminal device communicates with the network device based on the default AI characteristics in the third BWP configured by the second configuration information.

98. The terminal device according to any one of claims 73 to 97, characterized in that: The first configuration information includes one or more of the following: The first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP and the parameter set of the first BWP.

99. The terminal device according to any one of claims 73 to 98, characterized in that: The terminal device further includes a sending unit, the sending unit being configured to send capability information to the network device, the capability information being configured to indicate one or more of the following: A model supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; The terminal device supports AI features that can be used for the first BWP.

100. The terminal device as claimed in claim 99, characterized in that: The capability information is used to indicate the models supported by the terminal device and available for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device and available for the first BWP and used to implement the first AI function.

101. The terminal device according to claim 99 or 100, characterized in that: The capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes the model identifier of the model supported by the terminal device and available for use in the first BWP.

102. The terminal device according to claim 100 or 101, characterized in that: The capability information is used to indicate a default model among the models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

103. The terminal device according to any one of claims 100-102, characterized in that: The capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

104. The terminal device as claimed in claim 103, characterized in that: The capability information includes AI function identifiers of the one or more AI functions.

105. The terminal device according to claim 103 or 104, characterized in that: The capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

106. The terminal device according to any one of claims 100-105, characterized in that: The capability information is used to indicate the AI ​​features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

107. The terminal device according to claim 106, characterized in that: The capability information includes AI feature identifiers of the one or more AI features.

108. The terminal device according to claim 106 or 107, characterized in that: The capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

109. A network device, characterized in that: include: A sending unit, configured to send first configuration information to a terminal device, wherein the first configuration information is used to configure one or more of the following for the first bandwidth part BWP: First model; First artificial intelligence AI function; First AI feature.

110. The network device according to claim 109, characterized in that The first configuration information is used to configure one or more models that implement a first AI function, and the one or more models include the first model.

111. The network device according to claim 110, characterized in that The first configuration information includes model identifications of the one or more models.

112. The network device according to claim 110 or 111, characterized in that: The first configuration information is used to indicate a first default model among the one or more models, and activation of the first default model is in response to activation of the first BWP.

113. The network device according to claim 112, characterized in that: The first configuration information is used to indicate the first default model among the multiple models, and the sending unit is used to: Sending first indication information to the terminal device, where the first indication information is used to indicate activation of other models among the multiple models except the first default model.

114. The network device according to claim 113, characterized in that The network device further includes a first processing unit, wherein the first processing unit is configured to: In response to sending the first indication information, starting a first timer; During the running of the first timer, communication is performed with the terminal device based on the other model.

115. The network device according to claim 114, characterized in that The first processing unit is used for: In response to the first timer expiring, communicating with the terminal device based on the first default model.

116. The network device according to any one of claims 109 to 115, characterized in that: The first configuration information is used to indicate one or more AI functions supported by the first BWP, where the one or more AI functions include the first AI function.

117. The network device according to claim 116, characterized in that The first configuration information includes AI function identifiers of the one or more AI functions.

118. The network device according to claim 116 or 117, characterized in that: The first configuration information is used to indicate a first default AI function among the one or more AI functions, and activation of the first default AI function is in response to activation of the first BWP.

119. The network device according to any one of claims 116 to 118, characterized in that: The first configuration information is used to indicate the first default AI function among the multiple AI functions, and the sending unit is used to: Sending second indication information to the terminal device, where the second indication information is used to indicate activation of other AI functions among the multiple AI functions except the first default AI function.

120. The network device according to claim 119, characterized in that The network device further includes a second processing unit, wherein the second processing unit is configured to: In response to sending the second indication information, starting a second timer; While the second timer is running, communicating with the terminal device based on the other AI function.

121. The network device according to claim 120, characterized in that The second processing unit is used for: In response to the second timer timing out, communicating with the terminal device based on the first default AI function.

122. The network device according to any one of claims 109-121, characterized in that The first configuration information is used to indicate one or more AI features supported by the first BWP, where the one or more AI features include the first AI feature.

123. The network device according to claim 122, characterized in that The first configuration information includes AI feature identifiers of the one or more AI features.

124. The network device according to claim 121 or 122, characterized in that: The first configuration information is used to indicate a first default AI feature among the one or more AI features, and activation of the first default AI feature is in response to activation of the first BWP.

125. The network device according to any one of claims 122-124, characterized in that: The first configuration information is used to indicate the first default AI feature among the multiple AI features, and the sending unit is further used to: Sending third indication information to the terminal device, where the third indication information is used to indicate activation of other AI features among the multiple AI features except the first default AI feature.

126. The network device of claim 125, wherein: The network device further includes a third processing unit, and the third processing unit is configured to: In response to sending the third indication information, starting a third timer; During the running of the third timer, communicating with the terminal device based on the other AI characteristics.

127. The network device according to claim 126, characterized in that The third processing unit is used for: In response to the third timer timing out, communicating with the terminal device based on the first default AI characteristic.

128. The network device according to any one of claims 109 to 127, characterized in that: The network device further includes a fourth processing unit, and the fourth processing unit is configured to: In response to activating the first BWP, communicating with the terminal device based on the first configuration information.

129. The network device according to claim 128, characterized in that The activating the first BWP includes the terminal device switching from a second BWP to the first BWP, where the second BWP is different from the first BWP.

130. The network device according to claim 128 or 129, characterized in that: The fourth processing unit is used for: In response to activating the first BWP, starting a fourth timer; During the running of the fourth timer, communicate with the terminal device based on the first configuration information.

131. The network device of claim 130, wherein: The fourth processing unit is used for: In response to the fourth timer timing out, communicating with the terminal device based on second configuration information, where the second configuration information is used to configure one or more of the following for the third BWP: a second model; a second AI function; and a second AI characteristic.

132. The network device according to claim 131, characterized in that The third BWP is the default BWP.

133. The network device according to claim 131 or 132, characterized in that: The network device communicating with the terminal device based on the second configuration information includes one of the following: The network device communicates with the terminal device based on a default model in the third BWP configured by the second configuration information; The network device communicates with the terminal device based on the default AI function in the third BWP configured by the second configuration information; The network device communicates with the terminal device based on the default AI characteristics in the third BWP configured by the second configuration information.

134. The network device according to any one of claims 109 to 133, characterized in that The first configuration information includes one or more of the following: The first configuration information includes one or more of the following: the frequency domain position of the first BWP; the frequency bandwidth of the first BWP and the parameter set of the first BWP.

135. The network device according to any one of claims 109-134, characterized in that: The network device also includes: A receiving unit, configured to receive capability information sent by the terminal device, wherein the capability information is used to indicate one or more of the following: A model supported by the terminal device and available for the first BWP; AI functions supported by the terminal device and available for the first BWP; The terminal device supports AI features that can be used for the first BWP.

136. The network device according to claim 135, characterized in that The capability information is used to indicate the models supported by the terminal device and available for the first BWP, and the capability information is used to indicate one or more models supported by the terminal device and available for the first BWP and used to implement the first AI function.

137. The network device according to claim 135 or 136, characterized in that: The capability information is used to indicate the models supported by the terminal device and available for use in the first BWP, and the capability information includes the model identifier of the model supported by the terminal device and available for use in the first BWP.

138. The network device according to claim 136 or 137, characterized in that: The capability information is used to indicate a default model among the models supported by the terminal device and available for the first BWP, and activation of the default model is in response to activation of the first BWP.

139. The network device according to any one of claims 135 to 138, characterized in that: The capability information is used to indicate the AI ​​functions supported by the terminal device and available for the first BWP, where the AI ​​functions available for the first BWP include one or more AI functions.

140. The network device of claim 139, wherein: The capability information includes AI function identifiers of the one or more AI functions.

141. The network device according to claim 139 or 140, characterized in that: The capability information is used to indicate a default AI function among the AI ​​functions supported by the terminal device and available for the first BWP, and activation of the default AI function is in response to activation of the first BWP.

142. The network device according to any one of claims 135 to 141, characterized in that: The capability information is used to indicate the AI ​​features supported by the terminal device and available for the first BWP, where the AI ​​features available for the first BWP include one or more AI features.

143. The network device according to claim 142, characterized in that The capability information includes AI feature identifiers of the one or more AI features.

144. The network device according to claim 142 or 143, characterized in that: The capability information is used to indicate a default AI feature among the AI ​​features supported by the terminal device and available for the first BWP, and activation of the default AI feature is in response to activation of the first BWP.

145. A terminal device, characterized in that: It comprises a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the terminal device executes the method as described in any one of claims 1-36.

146. A network device, characterized in that: It includes a transceiver, a memory and a processor, wherein the memory is used to store programs, and the processor is used to call the programs in the memory and control the transceiver to receive or send signals so that the network device executes the method as described in any one of claims 37-72.

147. A device, characterized in that: It includes a processor for calling a program from a memory so that the device executes a method as described in any one of claims 1-72.

148. A chip, characterized in that: It comprises a processor for calling a program from a memory so that a device equipped with the chip executes a method as described in any one of claims 1 to 72.

149. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing a computer to execute the method as claimed in any one of claims 1 to 72.

150. A computer program product, characterized in that Comprising a program, the program causing a computer to execute the method as described in any one of claims 1-72.

151. A computer program, characterized in that The computer program causes a computer to execute the method according to any one of claims 1 to 72.

Images