Wireless communication method and communication equipment

Abstract

The invention provides a wireless communication method and communication equipment. The method comprises: a first device determining first information, the first information comprising one or more of the following: a first public identifier associated with a first model for wireless communication; and the first local identifier is associated with the first model and / or the first public identifier. In the embodiment of the invention, the first equipment can determine the first information used for indicating the first model, so that the first model can be indicated in the wireless communication system.

Description

Wireless communication method and communication device Technical Field

[0001] The present application relates to the field of communication technology, and more specifically, to a wireless communication method and communication device. Background Art

[0002] With the development of artificial intelligence (AI) technology, models based on AI technology (for example, AI models or machine learning models) have been widely used in various wireless communication processes, which has greatly increased the number of models used in wireless communication processes. In some scenarios, in order to ensure the accuracy of the model output results, different models can be used for different problems, different models can be used for different execution entities, different models can be used for different usage environments, different models can be used for different input data, and different models can be used for different target accuracies. In other scenarios, different models can be used even for the same problem, and even for the same model, different execution entities can have different model deployment solutions and model optimization solutions. As a result, how to indicate different models in wireless communication systems has become an urgent problem to be solved.

[0003] Summary of the Invention

[0004] The present application provides a wireless communication method and a communication device. The following introduces various aspects of the present application.

[0005] In a first aspect, a method for wireless communication is provided, including: a first device determines first information, wherein the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; a first local identifier associated with the first model and / or the first public identifier.

[0006] In a second aspect, a method for wireless communication is provided, including: a second device receives first information sent by a first device, the first information including one or more of the following: a first public identifier associated with a first model for wireless communication; a first local identifier associated with the first model and / or the first public identifier.

[0007] According to a third aspect, a communication device is provided, which is a first device and includes: a determination unit for determining first information, wherein the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; a first local identifier associated with the first model and / or the first public identifier.

[0008] In a fourth aspect, a communication device is provided, which is a second device and includes: a receiving unit for receiving first information sent by a first device, wherein the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; a first local identifier associated with the first model and / or the first public identifier.

[0009] In a fifth aspect, a communication device is provided, comprising 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 executes a method as described in any one of the aspects.

[0010] In a sixth aspect, a device is provided, comprising a processor, configured to call a program from a memory so that the device executes a method as described in any one of the aspects.

[0011] In a seventh aspect, a chip is provided, comprising 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 the aspects.

[0012] In an eighth aspect, a computer-readable storage medium is provided, on which a program is stored, wherein the program enables a computer to execute the method as described in any one of the aspects.

[0013] In a ninth aspect, a computer program product is provided, comprising a program, wherein the program enables a computer to execute the method as described in any one of the aspects.

[0014] In a tenth aspect, a computer program is provided, which enables a computer to execute the method as described in any one of the aspects.

[0015] In an embodiment of the present application, the first device can determine first information for indicating the first model, which helps to indicate the first model in the wireless communication system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] FIG1 is a diagram illustrating an example of a system architecture of a wireless communication system to which an embodiment of the present application may be applied.

[0017] FIG2 is a schematic diagram of channel estimation and signal recovery applicable to an embodiment of the present application.

[0018] FIG3 is a schematic diagram of a process of performing channel estimation based on an AI decoder.

[0019] FIG4 is a schematic diagram of a CSI feedback system based on an autoencoder.

[0020] FIG5 is a schematic diagram of a receiver based on an AI decoder.

[0021] FIG6 is a schematic diagram of beam selection based on the AI ​​model.

[0022] FIG7 is a schematic diagram of a positioning solution based on an AI model.

[0023] FIG8 is a schematic diagram of a neural network applicable to an embodiment of the present application.

[0024] Figure 9 is a schematic diagram of a convolutional neural network applicable to an embodiment of the present application.

[0025] FIG10 is a schematic flowchart of a wireless communication method according to an embodiment of the present application.

[0026] FIG11 is a schematic diagram of an information transmission method according to an embodiment of the present application.

[0027] FIG12 is a schematic diagram of an information transmission method according to another embodiment of the present application.

[0028] FIG13 is a schematic diagram of a communication device according to an embodiment of the present application.

[0029] FIG14 is a schematic diagram of a communication device according to an embodiment of the present application.

[0030] FIG15 is a schematic structural diagram of a device according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The technical solutions of the present application will be described below with reference to the accompanying drawings. For ease of understanding, the following first introduces the communication system applicable to the embodiments of the present application, as well as the terminology and communication process involved, with reference to Figures 1 to 9.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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, a modem or a 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.

[0038] 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.

[0039] 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 includes a CU and a DU. The gNB may also include an AAU.

[0040] 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.

[0041] 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).

[0042] With the development of artificial intelligence (AI) technology, AI models are being introduced into more and more communication processes. For ease of understanding, the following uses an autoencoder as an AI model as an example, and introduces the use of the autoencoder in the communication process in conjunction with Figures 2 to 5. It should be noted that the AI ​​model applicable to the embodiments of the present application (hereinafter referred to as the "first model") is not limited to the autoencoder.

[0043] An autoencoder is a neural network that uses an input signal as a training target. The architecture of the AI ​​encoder and / or AI decoder it contains is naturally compatible with many architectures in communication systems. For example, the AI ​​encoder and AI decoder can correspond to the transmitter and receiver of a wireless communication system, respectively. For another example, the AI ​​encoder and AI decoder can also correspond to the channel compression module and decompression module in the CSI feedback process, respectively. For another example, the AI ​​decoder in the autoencoder can also be used alone in the channel estimation process for the receiver to recover the channel information. The following will be introduced in conjunction with Figures 2 to 4, and for the sake of brevity, it will not be repeated here.

[0044] Typically, before deploying an autoencoder in a communication system, the autoencoder can be trained based on a training set. For example, if the autoencoder only includes an AI decoder, the AI ​​decoder can be trained based on the training set. If the autoencoder also includes an AI encoder, the AI ​​encoder can be trained based on the training set. If the autoencoder includes both the AI ​​encoder and the AI ​​decoder, the AI ​​encoder and the AI ​​decoder can be trained jointly.

[0045] In some implementations, since the autoencoder is a neural network model that uses the input signal as a training target, when the difference between the input and output of the autoencoder is represented by the loss function, the training goal of the autoencoder can be understood as optimizing the weights of the AI ​​encoder and AI decoder while minimizing the loss function.

[0046] For example, an autoencoder consisting of an AI encoder f(·) and an AI decoder g(·) is represented as g(f(·)). The original signal s is first encoded by the AI ​​encoder f(·), and the encoded signal output by the AI ​​encoder f(·) is represented as q = f(s). When the encoded signal is input into the AI ​​decoder g(·) for decoding, the decoded signal output by the AI ​​decoder g(·) is represented as s` = g(q) = g(f(s)). In the joint training stage, min_ {g,f} The AI ​​encoder f(·) and AI decoder g(·) are jointly trained with l(s,g(f(s))) as the training target, where l(·) represents the loss function.

[0047] Channel estimation based on AI decoder

[0048] Due to the complexity and time-varying nature of wireless channel environments, in wireless communication systems (e.g., the wireless communication systems described above), a receiver needs to recover received signals based on channel estimation results. Figure 2 is a schematic diagram of channel estimation and signal recovery applicable to embodiments of the present application.

[0049] As shown in FIG2 , in step S210 , the transmitter transmits, in addition to the data signal, a series of pilot signals known to the receiver on the time-frequency resources, such as the channel state information-reference signal (CSI-RS) and the demodulation reference signal (DMRS).

[0050] In step S211, the transmitter transmits the above data signal and pilot signal to the transmitter through the channel.

[0051] In step S212, after receiving the pilot signal, the receiver may perform channel estimation. In one possible implementation, the receiver may estimate channel information of the channel transmitting the pilot signal based on a pre-stored pilot sequence and the received pilot sequence using a channel estimation algorithm (e.g., a least squares (LS) channel estimation method).

[0052] In step S213, the receiver may recover the channel information on all time-frequency resources using an interpolation algorithm based on the channel information of the channel transmitting the pilot sequence, for subsequent channel state information (CSI) feedback or data recovery.

[0053] Channel estimation based on the AI ​​decoder aims to use the AI ​​decoder to process the pilot signal received by the receiver to achieve channel estimation. Figure 3 shows the process of channel estimation based on the AI ​​decoder. Referring to Figure 3, the pilot signal received by the receiver 300 is used as the input of the AI ​​decoder 310. Accordingly, the AI ​​decoder 310 processes the input pilot signal to output channel information. In addition, in some implementations, other auxiliary information can be added in addition to the pilot signal to improve the accuracy of the channel information output by the AI ​​decoder. For example, the original sequence of the pilot signal pre-stored by the receiver 300, the energy level of the pilot signal received by the receiver 300, the transmission delay when transmitting the pilot signal, or the noise when transmitting the pilot signal, etc. can also be input to the AI ​​decoder 310.

[0054] CSI feedback based on autoencoder

[0055] 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.

[0056] Figure 4 shows a CSI feedback system based on an autoencoder. As shown in Figure 4, the entire feedback system includes the AI ​​encoder 411 and AI decoder 421 parts 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. 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.

[0057] AI decoder-based receiver

[0058] By introducing an AI decoder into the receiver design and using it to perform signal processing within the receiver (e.g., demodulation, decompression, etc.), receiver performance can be improved. Figure 5 is a schematic diagram of a receiver based on an AI decoder. In the receiver 500 shown in Figure 5, the input of the AI ​​decoder 510 is the received signal received by the receiver, and the output is the decoded signal.

[0059] As can be seen from the above introduction, modular communication system design based on autoencoders is a trend in the development of communication systems. It can make good use of the prior structure of traditional communication system models, and can also flexibly adjust and train the AI ​​encoder and / or AI decoder in the autoencoder.

[0060] In some scenarios, AI models can also be used for beam management. The following describes the beam management process based on the AI ​​model in conjunction with Figure 6.

[0061] AI-based beam management

[0062] 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.

[0063] 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.

[0064] 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.

[0065] 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.

[0066] 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.).

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] In some other implementations, the beam set B may be exactly the same as the beam set A.

[0076] Positioning based on AI models

[0077] In cellular wireless positioning, the straight-line propagation of electromagnetic waves between network devices and terminal 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 usually called 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 environments where NLOS is predominant. In most scenarios, the number of network devices with LOS channels to terminal devices is often small, resulting in the inability of traditional positioning algorithms to meet the requirements of high-precision positioning. In addition, there may be some non-ideal factors in actual systems, which can lead to reduced positioning accuracy.

[0078] 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.

[0079] FIG7 shows a schematic diagram of an AI model-based positioning solution applicable to an embodiment of the present application. Referring to FIG7 , in a positioning solution based on an AI model 710 in a LOS / NLOS channel coexistence scenario, the channel response can be used as the input of the AI ​​model 710, and the position coordinates can be used as the output of the AI ​​model 710. The AI ​​model 710 learns the intrinsic relationship between the wireless channel and the position 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 710 can also output the position coordinates of the terminal device with higher accuracy, which helps to meet the needs of high-precision positioning.

[0080] 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.

[0081] Neural Networks

[0082] 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.

[0083] As shown in Figure 8, neurons can rely on activation functions to implement nonlinear mapping, where the input of the neuron can be recorded as A, and each dimension of the input is recorded as a j , the corresponding weight is recorded as w j , together with the summation units (SU), the input is strengthened or weakened. In addition, the output of SU can be input into the activation function f to obtain the output t, where the value of j is 1, 2, ..., n.

[0084] Common neural networks include convolutional neural network (CNN), recurrent neural network (RNN), deep neural network (DNN), etc.

[0085] The following describes a neural network applicable to embodiments of the present application in conjunction with FIG8 . The neural network shown in FIG8 can be divided into three categories based on the location of different layers: input layer 810 , hidden layer 820 , and output layer 830 . Generally speaking, the first layer is the input layer 810 , the last layer is the output layer 830 , and the intermediate layers between the first and last layers are all hidden layers 820 .

[0086] The input layer 810 is used to input data, where the input data can be, for example, a received signal received by a receiver. The hidden layer 820 is used to process the input data, for example, decompress the received signal. The output layer 830 is used to output processed output data, for example, a decompressed signal.

[0087] As shown in Figure 8, a neural network consists of multiple layers, each layer 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.

[0088] 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.

[0089] CNN is a deep neural network with a convolutional structure, and its structure is shown in FIG9 , which may include an input layer 910 , a convolutional layer 920 , a pooling layer 930 , a fully connected layer 940 , and an output layer 950 .

[0090] Each convolution layer 920 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.

[0091] 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.

[0092] 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.

[0093] Pooling layer 930 is often needed to reduce the number of training parameters. Therefore, it is often necessary to periodically introduce pooling layers after convolutional layers. For example, as shown in Figure 9, a single convolutional layer can be followed by a pooling layer, or multiple convolutional layers can be followed by one or more pooling layers. In signal processing, the sole purpose of the pooling layer is to reduce the spatial size of the extracted information.

[0094] The fully connected layer 940, after being processed by the convolution layer 920 and the pooling layer 930, is not sufficient for CNN to output the required output information. Because as mentioned above, the convolution layer 920 and the pooling layer 930 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 940. Generally, the fully connected layer 940 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.

[0095] Following the multiple hidden layers in the fully connected layer 940, the final layer of the CNN is the output layer 950, which is used to output the results. Typically, this output layer 950 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 output of the CNN model (also known as the predicted value) and the ideal result (also known as the true value).

[0096] To minimize the loss function, the CNN model needs to be trained. In some implementations, the backpropagation algorithm (BP) can be used to train the CNN model. 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 910 to 950 in Figure 9 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 of the output layer differs significantly from the ideal result, the minimization of the aforementioned loss function is used as the optimization goal, and the backpropagation process is switched to (e.g., the propagation from 950 to 910 in Figure 9 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.

[0097] It should be noted that the CNN shown in Figure 9 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.

[0098] 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.

[0099] 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, the output must be propagated back three steps, and the gradients of the three subsequent steps must be added. This learning algorithm is called backpropagation through time (BPTT).

[0100] 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.

[0101] As previously mentioned, with the development of AI technology, models based on AI technology (e.g., AI models or ML models) have been widely used in various wireless communication processes, greatly increasing the number of models used in wireless communication processes. In some scenarios, to ensure the accuracy of model output results, different models can be used for different problems, different models can be used for different execution entities, different models can be used for different usage environments, different models can be used for different input data, and different models can be used for different target accuracies. In other scenarios, different models can be used even for the same problem, and even for the same model, different execution entities can have different model deployment solutions and model optimization solutions. As a result, how to indicate different models in wireless communication systems has become an urgent problem that needs to be solved.

[0102] Therefore, to address the above problems, an embodiment of the present application provides a method for wireless communication, in which a first device can determine first information for indicating a model (hereinafter referred to as the "first model"), which helps to indicate the first model in a wireless communication system.

[0103] For ease of understanding, the wireless communication method according to an embodiment of the present application is described below in conjunction with Figure 10. Figure 10 is a schematic flow chart of the wireless communication method according to an embodiment of the present application. The method shown in Figure 10 includes step S1010.

[0104] In step S1010, a first device determines first information. The first device may be a terminal device or a network device, wherein the network device may be, for example, an access network device or a core network device, which is not limited in this embodiment of the present application.

[0105] In some implementations, the first information may include a first public identifier, where the first public identifier is associated with the first model used for wireless communication, or in other words, the first public identifier is used to identify the first model. For example, the first public identifier is used to uniquely identify the first model within a first scope, where the first scope may include, for example, global, national, regional, and institutional, etc., although this embodiment of the present application does not limit this.

[0106] It should be noted that the embodiments of the present application do not limit the scenario in which the first information is determined. For example, the first information may be determined while the first device is using the first model. For another example, the first information may be determined when the first device updates the first model. For another example, the first information may be determined when the first device manages the first model, where managing the first model may include, for example, activating and / or deactivating the first model.

[0107] In some implementations, the first public identifier may include a first identifier, wherein the first identifier is used to identify the scope of use of the first model. The following uses the third identifier and the fourth identifier as examples to describe the implementation of the first identifier in the embodiments of the present application.

[0108] In implementation 1, the first identifier may include a third identifier for identifying one or more regions. Accordingly, the first model may be used within the region indicated by the third identifier. Regions may include, for example, any regional level, such as country, state, province, city, county, etc. Of course, in the embodiment of the present application, regions may not be divided according to regional levels. For example, regions may include country A and province C of country B. This embodiment of the present application is not limited to this.

[0109] For example, if the first identifier includes a third identifier for identifying a country, the third identifier can be called a country identifier or a region identifier. In some implementations, N bits can be used as the country identifier, for example, an 8-bit country identifier. In other implementations, N numbers can be used as the country identifier, for example, a 3-digit decimal number can be used as the country identifier. This embodiment of the present application is not limited to this.

[0110] For example, if the first identifier includes a third identifier for identifying a region (e.g., a state, province, city, or county), the third identifier can be referred to as a region identifier. In some implementations, M bits can be used as the region identifier, for example, the region identifier can be 8 bits. In other implementations, M numbers can be used as the region identifier, for example, the region identifier can be represented by a 4-digit decimal number. This is not limited in the present embodiment.

[0111] It should be noted that in some implementations, when the third identifier is used to identify multiple regions, the multiple regions may correspond to different scopes of use of the first model. For example, the multiple regions may include multiple different countries, and the third identifier may include the region identifiers corresponding to the multiple countries. Accordingly, the first model can be used in multiple countries.

[0112] In other implementations, when the third identifier is used to identify multiple regions, the multiple regions may include multiple regions with varying ranges. In other words, the third identifier includes the region identifiers of the multiple regions with varying ranges. In this case, the multiple regions can jointly indicate the scope of use of a first model. For example, the multiple regions may include Province B in Country A, and the third identifier may include the region identifier of Country A and the region identifier of Province B. Accordingly, the first model can be used within Province B in Country A.

[0113] In addition, in the embodiment of the present application, a region may correspond to a region identifier, for example, the country identifier corresponding to country A may be country ID 1. Of course, a region may also correspond to multiple region identifiers, for example, the country identifier corresponding to country A may include country ID 1 and country ID 2.

[0114] In implementation 2, the first identifier may include a fourth identifier for identifying one or more organizations. Therefore, the fourth identifier may also be referred to as an organization identifier. Accordingly, the first model may be used within the organization corresponding to the fourth identifier.

[0115] In some implementations, the aforementioned organization may be an organization associated with the first model, for example, the organization that provides the first model. Assuming that Model A, the first model, is provided by Operator A, the aforementioned organization may include an organization corresponding to Operator A. Accordingly, the organization identifier corresponding to Model A is used to identify Operator A.

[0116] For another example, the mechanism may be a mechanism for optimizing the first model. Assuming that model A as the first model is optimized by device A, the mechanism may include a mechanism corresponding to device A. Accordingly, the mechanism identifier corresponding to model A is used to identify device A.

[0117] In the embodiments of the present application, the specific representation of the organization identifier is not limited. In some implementations, K bits can be used as the organization identifier, for example, the organization identifier can be 16 bits. In other implementations, K numbers can be used as the organization identifier, for example, the organization identifier can be represented by 6 decimal numbers.

[0118] In some scenarios, the first model may be optimized by different devices (for example, terminal devices, network devices, etc.) (for ease of description, the device that optimizes the model will be referred to as the optimization device below). Since the optimization process or optimization data used by different optimization devices when optimizing the first model are different, the optimized model may only be applicable to the optimization device locally, or in other words, the result of the model output after optimization in the optimization device has a higher accuracy rate. Therefore, in an embodiment of the present application, the mechanism identifier corresponding to the model optimized by different optimization devices can be used to identify the optimization device, so that the optimized model can be used locally in the optimization device, which helps to improve the accuracy of the model output results. This avoids the problem that the optimization device is different from the device using the model, resulting in a lower accuracy rate of the optimized model output results. Of course, in an embodiment of the present application, if the above problems are not considered, the optimized model can also be used on other devices other than the optimization device.

[0119] Assume that the original model running on device A and device B is model A, and to improve the accuracy of model A, device A optimizes model A and obtains version A1 of model A. Then the organization ID corresponding to version A1 of model A can be used to identify device A. In addition, to improve the accuracy of model A, device B optimizes model A and obtains version A2 of model A. Then the organization ID corresponding to version A2 of model A can be used to identify device B. In this way, version A1 of model A can be used in device A, and version A2 of model A can be used in device B. Compared with the case where the optimized model A (i.e., version A1) of device A is run on device B, which may result in a decrease in the accuracy of the output of model A, it helps to improve the accuracy of the output results of different optimized versions of model A.

[0120] In the embodiment of the present application, the above-mentioned organization may be, for example, one or more of an operator, a network equipment manufacturer, a terminal equipment manufacturer, and a third-party model provider, and the embodiment of the present application does not limit this.

[0121] In some scenarios, there may be multiple organizations associated with the first model, for example, multiple organizations jointly train, optimize, and use the first model. Accordingly, the fourth identifier may be used to identify multiple organizations.

[0122] In some implementations, the different orders of the organization identifications among the multiple organizations included in the fourth identification can be used to identify different models. For example, the order of the multiple organization identifications included in the fourth identification corresponding to model A is organization identification 1, organization identification 2, and organization identification 3. The order of the multiple organization identifications included in the fourth identification corresponding to model B is organization identification 2, organization identification 1, and organization identification 3. In this case, model A and model B are different models. Of course, in the embodiment of the present application, the different orders of the organization identifications among the multiple organizations included in the fourth identification can be used to identify the same model.

[0123] In an embodiment of the present application, when the fourth identifier is used to identify multiple institutions, the fourth identifier may include the institution identifier corresponding to each of the multiple institutions. Of course, in an embodiment of the present application, when the fourth identifier is used to identify multiple institutions, the fourth identifier may include a joint institution identifier for identifying multiple institutions, wherein the joint institution code may be obtained by, for example, jointly encoding the institution identifiers of multiple institutions. This embodiment of the present application does not limit the specific method by which the fourth identifier identifies multiple institutions.

[0124] For example, the joint organization identifier may be 10 bits, which can represent up to 1024 different combinations of organizations. For another example, the joint organization identifier may include 3 decimal digits, which can represent up to 1000 different combinations of organizations.

[0125] In some implementations, the first public identifier may include a second identifier, where the second identifier is used to identify the model scheme of the first model. Therefore, the second identifier may also be called a model scheme identifier.

[0126] In the embodiments of the present application, the second identifier can be used to identify the model by its serial number, its task, and its characteristic attributes. For ease of understanding, the following descriptions are made in conjunction with the fifth, sixth, and seventh identifiers. It should be noted that the fifth, sixth, and seventh identifiers can be used individually or in combination, and are not limited in this embodiment of the present application.

[0127] Taking the example that the second identifier includes the fifth identifier, the fifth identifier is used to identify the serial number of the first model, or the fifth identifier is used to represent the serial number of the first model.

[0128] In the embodiments of the present application, the specific implementation of the fifth identifier is not limited. In some implementations, the fifth identifier can be N1 bits, for example, the fifth identifier can be 16 bits. Of course, in the embodiments of the present application, the fifth identifier can also be represented by N1 numbers, for example, the fifth identifier can include 4 decimal numbers. For ease of understanding, the fifth identifier of the embodiments of the present application is introduced below in conjunction with Tables 1 and 2.

[0129] Assuming that 16 bits are used to represent the fifth identifier, as shown in Table 1, if the fifth identifier is 0001, it can be used to identify model 1, if the fifth identifier is 0010, it can be used to identify model 2, if the fifth identifier is 1001, it can be used to identify model 3, and if the fifth identifier is 1100, it can be used to identify model 4.

[0130] Table 1

[0131] Fifth identification model scheme 0001 model 1 0010 model 2 1001 model 3 1100 model 4

[0132] Assuming that four decimal numbers are used to represent the fifth identifier, as shown in Table 2, if the fifth identifier is 0001, it can be used to identify model 1. If the fifth identifier is 0002, it can be used to identify model 2. If the fifth identifier is 0023, it can be used to identify model 3. If the fifth identifier is 0057, it can be used to identify model 4.

[0133] Table 2

[0134] Fifth identification model scheme 0001 model 1 0010 model 2 1001 model 3 1100 model 4

[0135] Taking the example that the second identifier includes the sixth identifier, the sixth identifier is used to identify the task of the first model, or the sixth identifier is used to represent the task of the first model.

[0136] In some implementations, the tasks of the first model can be understood as tasks performed by the first model. Therefore, the sixth identifier can also be referred to as a "task identifier." The tasks can include one or more of a CSI feedback enhancement task, a beam management task, a positioning task, a channel estimation task, a coding and decoding task, and a mobility management task.

[0137] In the embodiments of the present application, the specific implementation of the sixth identifier is not limited. In some implementations, the sixth identifier can be N2 bits. For example, the sixth identifier can be 8 bits, which can represent up to 256 different tasks. Of course, in the embodiments of the present application, the sixth identifier can also be represented by N2 numbers. For example, the sixth identifier can include 4 decimal numbers. For ease of understanding, the sixth identifier of the embodiments of the present application is introduced below in conjunction with Tables 3 and 4.

[0138] Assuming that 8 bits are used to represent the sixth identifier, as shown in Table 3, if the sixth identifier is 00000001, it can be used to identify the task of the model as CSI feedback enhancement. If the sixth identifier is 00000010, it can be used to identify the task of the model as beam management. If the sixth identifier is 00000011, it can be used to identify the task of the model as positioning enhancement. If the sixth identifier is 00000100, it can be used to identify the task of the model as channel estimation. If the sixth identifier is 00000101, it can be used to identify the task of the model as encoding and decoding. If the sixth identifier is 00000110, it can be used to identify the task of the model as mobility management. If the sixth identifier is any one of 00100100, 01010110, and 11001100, the task of the identified model is to be determined, that is, 00100100, 01010110, and 11001100 can be reserved identifiers.

[0139] Table 3

[0140] Tasks of the sixth identification model: 00000001 CSI feedback enhancement 00000010 Beam management 00000011 Positioning enhancement 00000100 Channel estimation 00000101 Codec 00000110 Mobility management 00100100 Reserved 01010110 Reserved 11001100 Reserved

[0141] Assuming that four decimal numbers are used to represent the sixth identifier, as shown in Table 4, if the sixth identifier is 0001, it can be used to identify the model's task as CSI feedback enhancement. If the sixth identifier is 0002, it can be used to identify the model's task as positioning enhancement. If the sixth identifier is 0023 or 0057, the task of the identified model is undetermined, that is, 0023 or 0057 can be reserved identifiers.

[0142] Table 4

[0143] Tasks of the sixth identification model 0001 CSI feedback enhancement 0002 Positioning enhancement 0023 Reserved 0057 Reserved

[0144] In other implementations, the tasks of the first model may also include subtasks in the tasks performed by the first model, or in other words, functions in the tasks performed by the first model. Therefore, the sixth identifier may also be called a "function identifier."

[0145] It should be noted that, in an embodiment of the present application, the subtask identified by the sixth identifier may be one or more subtasks. For example, if the first model is used to perform CSI feedback enhancement, the subtasks may include one or more of CSI compression, CSI prediction, and CSI prediction and compression. For another example, if the first model is used to perform beam management, the subtasks may include beam selection and / or beam prediction. For another example, if the first model is used for positioning enhancement, the subtasks may include direct positioning and / or indirect positioning.

[0146] In the embodiment of the present application, the specific implementation form of the sixth identifier is not limited. In some implementations, the sixth identifier can be N2 bits. For example, the sixth identifier can be 6 bits, which can represent up to 64 different subtasks. Of course, in the embodiment of the present application, the sixth identifier can also be represented by N2 numbers. For example, the sixth identifier can include 4 decimal numbers, which can represent up to 10,000 different subtasks. For ease of understanding, the sixth identifier of the embodiment of the present application is introduced below in conjunction with Tables 5 and 6.

[0147] Assuming that 6 bits are used to represent the sixth identifier and the first model is used to perform CSI feedback enhancement, as shown in Table 5, if the sixth identifier is 00000001, it can be used to identify the subtask of the model as CSI compression. If the sixth identifier is 00000010, it can be used to identify the subtask of the model as CSI prediction. If the sixth identifier is 00000011, it can be used to identify the subtask of the model as CSI compression and CSI prediction. If the sixth identifier is 10010011, the subtask of the identified model is to be determined, that is, 10010011 can be a reserved identifier.

[0148] Table 5

[0149] The sixth identification subtask 00000001CSI compression 00000010CSI prediction

[0150] 00100011CSI compression and CSI prediction 10010011 reserved

[0151] Assuming that four decimal numbers are used to represent the sixth identifier, and the first model is used to perform CSI feedback enhancement, as shown in Table 6, if the sixth identifier is 0001, it can be used to identify the subtask of the model as CSI compression. If the sixth identifier is 0002, it can be used to identify the subtask of the model as CSI prediction. If the sixth identifier is 0023 or 0057, the subtask of the identified model is undetermined, that is, 0023 or 0057 can be reserved identifiers.

[0152] Table 6

[0153] Sixth identification subtask 0001 CSI compression 0002 CSI prediction 0023 reserved 0057 reserved

[0154] Taking the example that the second identifier includes the seventh identifier, the seventh identifier is used to identify the characteristic attribute of the first model, or the seventh identifier is used to represent the characteristic attribute of the first model.

[0155] The characteristic attributes of the above-mentioned first model may, for example, include one or more of the model structure of the first model, the model platform of the first model, the interface of the first model, the performance of the first model, the training data of the first model, the quantization method of the first model, the complexity of the first model and the size of the first model. The embodiment of the present application does not specifically limit the characteristic attributes, and they will be introduced separately in conjunction with the eighth to fifteenth identifications below. For the sake of brevity, they will not be repeated here.

[0156] In the embodiments of the present application, the specific implementation of the seventh identifier is not limited. In some implementations, the seventh identifier can be N3 bits, for example, the seventh identifier can be 8 bits, and can represent up to 256 different characteristic attributes. Of course, in the embodiments of the present application, the seventh identifier can also be represented by N3 numbers, for example, the seventh identifier can include 4 decimal numbers.

[0157] Taking the example of the seventh identifier including the eighth identifier, the eighth identifier is associated with the model structure of the first model. For example, the eighth identifier is used to identify the model structure of the first model, or the eighth identifier is used to indicate the model structure of the first model. Therefore, the eighth identifier can also be called the "model structure identifier."

[0158] The above-mentioned model structure is also called a model type, and may include, for example, any of CNN, DNN, Residual Network (ResNet), Transformer, Mixer, Autoencoder, CsiNet, EVCsiNet, and EVCsiNet-T. Of course, in the embodiment of the present application, the above-mentioned model type may also include a model type newly introduced in the future, and the embodiment of the present application does not limit this.

[0159] In the embodiment of the present application, the specific implementation form of the eighth identifier is not limited. In some implementations, the eighth identifier can be N4 bits. For example, the eighth identifier can be 8 bits, which can represent up to 256 different model structures. Of course, in the embodiment of the present application, the eighth identifier can also be represented by N4 numbers. For example, the eighth identifier can include 3 decimal numbers, which can represent up to 1000 different model structures.

[0160] Taking the example of the seventh identifier including the ninth identifier, the ninth identifier is associated with the model platform of the first model. For example, the ninth identifier is used to identify the model platform of the first model, or the ninth identifier is used to indicate the model platform of the first model. Therefore, the ninth identifier can also be called the "model platform identifier."

[0161] In some implementations, the model platform may include any one of TensorFlow, PyTorch, ONNX, Caffe2, MXNet, ML.NET, TensorRT, and Microsoft CNTK. Of course, in the embodiments of the present application, the model platform may also include a model platform newly introduced in the future, which is not limited in the embodiments of the present application.

[0162] In the embodiment of the present application, the specific implementation form of the ninth identifier is not limited. In some implementations, the ninth identifier can be N5 bits. For example, the ninth identifier can be 8 bits, which can represent up to 256 different model platforms. Of course, in the embodiment of the present application, the ninth identifier can also be represented by N5 numbers. For example, the ninth identifier can include 3 decimal numbers, which can represent up to 1000 different model platforms.

[0163] Taking the example of the seventh identifier including the tenth identifier, the tenth identifier is associated with the interface of the first model. In some implementations, the tenth identifier is used to identify the interface of the first model, or the tenth identifier is used to indicate the interface of the first model. Therefore, the tenth identifier can also be referred to as the "interface identifier." In other implementations, the tenth identifier is used to identify the interface format of the first model, or the tenth identifier is used to indicate the interface format of the first model.

[0164] In some implementations, the format of the interface of the first model may include the size of the input data of the first model, the format of the input data of the first model, the size of the output result of the first model, and the format of the output result of the first model. For example, the format of the interface of the first model may include one or more of the following: transmit antenna dimension, receive antenna dimension, bandwidth dimension, sub-band dimension, number of air interface feedback, number of positioning information measurements of network devices, and number of beam measurements.

[0165] In the embodiments of the present application, the specific implementation of the tenth identifier is not limited. In some implementations, the tenth identifier can be N6 bits. For example, the tenth identifier can be 7 bits, which can represent up to 128 different interfaces. Of course, in the embodiments of the present application, the tenth identifier can also be represented by N6 numbers. For example, the tenth identifier can include 2 decimal numbers, which can represent up to 100 different interfaces.

[0166] In some scenarios, the first model may support multiple interfaces. For example, the multiple interfaces supported by the first model may include input interface 1 and output interface 1. In this case, the above-mentioned tenth identifier may be used to identify the multiple interfaces supported by the first model. In some implementations, the above-mentioned tenth identifier may include the interface identifier of each of the multiple interfaces. For example, the first model supports interface 1 and interface 2, and accordingly, the tenth identifier may include the interface identifier of interface 1 and the interface identifier of interface 2. Of course, in an embodiment of the present application, the above-mentioned tenth identifier may include a joint interface identifier of multiple interfaces, wherein the joint interface identifier may be obtained by, for example, jointly encoding the interface identifier of each interface in the multiple interfaces. For example, the first model supports interface 1 and interface 2, and accordingly, the tenth identifier may include the joint interface identifier of interface 1 and interface 2.

[0167] In the embodiments of the present application, the specific implementation of the joint interface identifier is not limited. In some implementations, the joint interface identifier can be N7 bits. For example, the tenth identifier can be 7 bits, which can represent up to 128 different interface combinations. Of course, in the embodiments of the present application, the tenth identifier can also be represented by N7 numbers. For example, the tenth identifier can include 2 decimal numbers, which can represent up to 100 different interface combinations.

[0168] For example, the seventh identifier includes the eleventh identifier, and the eleventh identifier is associated with the performance of the first model. In some implementations, the eleventh identifier is used to identify the performance of the first model, or the eleventh identifier is used to indicate the performance of the first model. Therefore, the eleventh identifier can also be called a "performance identifier."

[0169] For example, the performance of the first model may include different levels of CSI recovery accuracy. For another example, the performance of the first model may include different levels of CSI prediction accuracy. For another example, the performance of the first model may include different levels of beam selection accuracy. For another example, the performance of the first model may include different levels of beam prediction accuracy. For another example, the performance of the first model may include different levels of positioning accuracy. For another example, the performance of the first model may include different levels of channel estimation accuracy. For another example, the performance of the first model may include different levels of system throughput efficiency brought about by the first model. For another example, the performance of the first model may include different levels of BLER brought about by the first model. For another example, the performance of the first model may include different levels of handover failure count brought about by the first model. For another example, the performance of the first model may include different levels of ping-pong handover count brought about by the first model, which is not specifically limited in the embodiments of the present application.

[0170] In the embodiments of the present application, the specific implementation of the eleventh identifier is not limited. In some implementations, the eleventh identifier can be N7 bits. For example, the eleventh identifier can be 4 bits, which can represent up to 16 different performances. Of course, in the embodiments of the present application, the eleventh identifier can also be represented by N7 numbers. For example, the eleventh identifier can include 1 decimal number, which can represent up to 10 different performances.

[0171] Taking the example of the seventh identifier including the twelfth identifier, the twelfth identifier is associated with the training data of the first model. In some implementations, the twelfth identifier is used to identify the amount of training data of the first model, or the twelfth identifier is used to indicate the amount of training data of the first model. In other implementations, the twelfth identifier is used to identify the data type of the training data of the first model, or the twelfth identifier is used to indicate the data type of the training data of the first model. Therefore, the twelfth identifier can also be referred to as a "training data identifier."

[0172] In the embodiments of the present application, the specific implementation of the twelfth identifier is not limited. In some implementations, the twelfth identifier can be N8 bits. For example, the twelfth identifier can be 7 bits, which can represent up to 128 different types of training data. Of course, in the embodiments of the present application, the twelfth identifier can also be represented by N8 numbers. For example, the twelfth identifier can include 2 decimal numbers, which can represent up to 100 different types of training data.

[0173] Taking the example that the seventh identifier includes the thirteenth identifier, the thirteenth identifier is associated with the quantization method of the first model. In some implementations, the thirteenth identifier is used to identify the quantization method of the first model, or the thirteenth identifier is used to indicate the quantization method of the first model. Therefore, the thirteenth identifier can also be called a "quantization method identifier". In other implementations, the thirteenth identifier is used to identify the dequantization method of the first model, or the thirteenth identifier is used to indicate the dequantization method of the first model. Of course, in the embodiment of the present application, the above-mentioned thirteenth identifier can also be used to identify the overhead of the quantization method, or the above-mentioned thirteenth identifier can also be used to identify the accuracy of the quantization method, and the embodiment of the present application does not limit this.

[0174] In the embodiments of the present application, the above quantization methods are not specifically limited. For example, the above quantization methods may include one or more of vector quantization, scalar quantization, uniform quantization, non-uniform quantization, and AI-based quantization. Of course, in the embodiments of the present application, the above quantization methods may also include quantization methods that will be newly introduced in the future.

[0175] In the embodiment of the present application, the specific implementation of the thirteenth identifier is not limited. In some implementations, the thirteenth identifier can be N9 bits. For example, the thirteenth identifier can be 4 bits, which can represent up to 16 different quantization methods. Of course, in the embodiment of the present application, the thirteenth identifier can also be represented by N9 numbers. For example, the thirteenth identifier can include 2 decimal numbers, which can represent up to 100 different quantization methods.

[0176] Taking the example that the seventh identifier includes the fourteenth identifier, the fourteenth identifier is associated with the model complexity of the first model. In some implementations, the fourteenth identifier is used to identify the model complexity of the first model, or the fourteenth identifier is used to indicate the model complexity of the first model. Therefore, the fourteenth identifier can also be called a "model complexity identifier". In other implementations, the fourteenth identifier is used to identify the solution model complexity of the first model, or the fourteenth identifier is used to indicate the solution model complexity of the first model. Of course, in an embodiment of the present application, the above-mentioned fourteenth identifier can also be used to identify the overhead of the model complexity, or the above-mentioned fourteenth identifier can also be used to identify the accuracy of the model complexity, and the embodiment of the present application does not limit this.

[0177] In the embodiments of the present application, the model complexity is not specifically limited. For example, the model complexity may include one or more of vector quantization, scalar quantization, uniform quantization, non-uniform quantization, and AI-based quantization. Of course, in the embodiments of the present application, the model complexity may also include model complexities newly introduced in the future.

[0178] In the embodiment of the present application, the specific implementation form of the fourteenth identifier is not limited. In some implementations, the fourteenth identifier can be N10 bits. For example, the fourteenth identifier can be 4 bits, which can represent up to 16 different model complexities. Of course, in the embodiment of the present application, the fourteenth identifier can also be represented by N10 numbers. For example, the fourteenth identifier can include 2 decimal numbers, which can represent up to 100 different model complexities.

[0179] For example, if the seventh identifier includes the fifteenth identifier, the fifteenth identifier is associated with the size of the first model. In some implementations, the fifteenth identifier is used to identify the size of the first model. For example, the fifteenth identifier is used to indicate the class corresponding to the size of the first model. Therefore, the fifteenth identifier can also be called a "size class identifier."

[0180] In the embodiments of the present application, the specific implementation of the fifteenth identifier is not limited. In some implementations, the fifteenth identifier can be N11 bits. For example, the fifteenth identifier can be 4 bits, which can represent up to 16 different sizes. Of course, in the embodiments of the present application, the fifteenth identifier can also be represented by N11 numbers. For example, the fifteenth identifier can include 2 decimal numbers, which can represent up to 100 different sizes.

[0181] It should be noted that in some implementations, the various identifiers described above can be used independently. Assuming that the scope of use of Model A is within the scope of use of Operator A, and that other operators will not use Model A, the public identifier of Model A may not include the organization identifier corresponding to Operator A, but only the fifth identifier used to identify the serial number of Model A.

[0182] In other implementations, the various identifiers described above can also be used in combination. For ease of understanding, the following uses the combination of an organization identifier and a task identifier as an example. It should be noted that the schemes for combining other identifiers are similar to the scheme for combining an organization identifier and a task identifier, and for the sake of brevity, they are not listed one by one below.

[0183] For example, suppose that organization A needs to determine the public identifier of model A, and organization B needs to determine the public identifier of model B. Models A and B perform the same task. In this case, if only the task identifier is used as the public identifier to identify models A and B, the public identifiers of models A and B may be the same, resulting in a public identifier conflict. Therefore, in order to ensure that the public identifier can uniquely identify the model, the organization identifier and the task identifier can be used as the public identifier to identify the model. Since organizations A and B correspond to different organization identifiers, the public identifier that includes the organization identifier can uniquely identify models A and B.

[0184] As mentioned above, the model can be uniquely identified by the public identifier, which helps to ensure that the model can be determined by the public identifier within the scope of use of the model (for example, globally, within a specific country, within a region, or within an organization). However, in some scenarios, the scope of use of the model may include a large number of models. Therefore, if you want to uniquely identify the model by the public identifier to avoid the situation where different models correspond to the same public identifier, the public identifier usually needs to occupy a larger number of bits, resulting in more air interface resources required for transmitting the public identifier. In particular, when the public identifier is transmitted through control information (such as DCI or UCI), the overhead of transmitting the control information will increase dramatically.

[0185] On the other hand, while there are many models within the scope of model usage, the number of models available to model users (e.g., a network, a network device, or a terminal device) is relatively small. In this case, if a public identifier is still used to identify the model between model users, more air interface resources will be required to transmit the public identifier.

[0186] Therefore, to avoid the above-mentioned problems, embodiments of the present application further provide a local identifier for indicating a model. Since the local identifier only needs to identify the model locally within the model user, the number of models that the local identifier needs to identify is smaller than that of the public identifier. In other words, the number of bits occupied by the local identifier is smaller than that occupied by the public identifier, which helps to reduce the air interface resources required for indicating the model. Of course, in embodiments of the present application, the number of bits occupied by the local identifier may be greater than or equal to the number of bits occupied by the public identifier, and this embodiment of the present application does not limit this.

[0187] In some implementations, the first information may include a first local identifier, wherein the first local identifier may be associated with the first model, or in other words, the first local identifier is used to identify the first model. Of course, in embodiments of the present application, the first local identifier may be associated with the first public identifier, so that the first local identifier can indicate the first model through the associated first public identifier.

[0188] In the embodiment of the present application, the specific implementation of the association relationship between the local identifier and the public identifier is not limited. In some implementations, the above association relationship can be represented in the form of a table. For ease of understanding, the following is an introduction in conjunction with Table 7.

[0189] As shown in Table 7, the public identifier used to identify model 1 is 1024060120235536, and the corresponding local identifier is 01. The public identifier used to identify model 2 is 3051830524947264, and the corresponding local identifier is 02. The public identifier used to identify model 3 is 4633823385957274, and the corresponding local identifier is 03. The public identifier used to identify model 4 is 9488472901948372, and the corresponding local identifier is 04.

[0190] Table 7

[0191] Model public identifier local identifier

[0192] Model 1102406012023553601 Model 2305183052494726402 Model 3463382338595727403 Model 4948847290194837204

[0193] In some implementations, the first local identifier may include a local identifier corresponding to an operator; a local identifier corresponding to a network device; a local identifier corresponding to a terminal device; and a local identifier corresponding to a region.

[0194] Taking the example that the first local identifier includes the local identifier corresponding to the operator, it can be understood that the conversion from the public identifier to the local identifier can be an operator-level conversion, that is, the public identifier of the model usable within the operator is converted into a local identifier.

[0195] Taking the example that the first local identifier includes the local identifier corresponding to the network device, it can be understood that the conversion from the public identifier to the local identifier can be a conversion at the network device level, that is, the public identifier of the model usable in the network device is converted into a local identifier.

[0196] Taking the example that the first local identifier includes the local identifier corresponding to the terminal device, it can be understood that the conversion from the public identifier to the local identifier can be a conversion at the terminal device level, that is, the public identifier of the model usable in the terminal device is converted into a local identifier.

[0197] Taking the example of a first local identifier including a local identifier corresponding to a region, it can be understood that the conversion of a public identifier to a local identifier can be a regional-level conversion, that is, the public identifier of the model usable in the region is converted into a local identifier. The region can be described above, and a region can include, for example, a country, state, province, city, county, etc., which is not limited in this embodiment of the present application.

[0198] In the embodiments of the present application, the manner in which the above-mentioned association relationship is generated is not limited. For example, the above-mentioned association relationship may be configured by the first device or the second device. For another example, the above-mentioned association relationship may be predefined, for example, by one or more of the associated devices, network devices, and terminal devices corresponding to the operator or region.

[0199] It should be noted that the local identifiers corresponding to the same model may be different for different model users (e.g., a first device and a second device). For example, for the first device, the local identifier of model A may be local identifier 1, and for the second device, the local identifier of model A may be local identifier 2. Of course, in the embodiments of the present application, the local identifiers corresponding to the same model may be the same for different model users. For example, for the first device, the local identifier of model A may be local identifier 1, and for the second device, the local identifier of model A may be local identifier 1.

[0200] That is to say, when the first device and the second device do not belong to the same operator network, the local identification maintained by each of them and the association relationship with the public identification may not affect each other. Therefore, the above-mentioned association relationship maintained by the first device may be the same as or different from the above-mentioned association relationship maintained by the second device.

[0201] In an embodiment of the present application, model users may indicate the first model by transmitting first information to each other. For example, a first device may send the first information to a second device. In some scenarios, if the first device indicates the first model via a first local identifier, the first device may indicate the association between the first public identifier and the first local identifier to the second device via a second information message, so that the second device can determine the first public identifier via the first local identifier and the association, and then determine the first model via the first public identifier.

[0202] The embodiments of the present application do not limit the second information. In some implementations, the second information can be transmitted through signaling, wherein the signaling can include, for example, uplink control information (UCI), downlink control information (DCI), medium access control control element (MAC CE), radio resource control (RRC) signaling, RRC reconfiguration message, system broadcast, master information block (MIB), system information block (SIB), SIB1. In other implementations, the second information can be used as data transmission, that is, the second information can be transmitted through a data channel, wherein the data channel can include, for example, one or more of a physical downlink shared channel (PDSCH), a physical uplink shared channel (PUSCH), and a physical sidelink shared channel (PSSCH).

[0203] It should be noted that in the embodiments of the present application, the first information and the second information can be transmitted independently of each other, or the first information and the second information can be transmitted together, and the embodiments of the present application do not limit this. In addition, if the first information and the second information are transmitted independently, the embodiments of the present application do not limit the order in which the first information and the second information are transmitted. For example, the first information can be transmitted before the second information. For another example, the second information can be transmitted before the first information.

[0204] In addition, in an embodiment of the present application, the second device may be a terminal device or a network device. Among them, the network device may include an access network device and a core network device. In combination with the above introduction to the first device, it can be seen that if the first device and the second device are both terminal devices, the above information (first information and / or second information) can be transmitted between the terminal devices. If the first device and the second device are both network devices, the above information (first information and / or second information) can be transmitted between the network devices. If the first device is a network device and the second device is a terminal device, as shown in Figure 11, the above information (first information and / or second information) can be sent by the network device to the terminal device. If the first device is a terminal device and the second device is a network device, as shown in Figure 12, the above information (first information and / or second information) can be sent by the terminal device to the network device.

[0205] In the embodiments of the present application, the scenario for transmitting the above information is not limited. In some implementations, the above information can be transmitted while the first model is in use. For another example, the above information can be transmitted when the first model is updated. For another example, the above information can be transmitted when managing the first model, where managing the first model can include activating and / or deactivating the first model.

[0206] For example, the network device may use the first model locally and associate the first model with the local identifier. Thereafter, during use, management, or update of the first model, the network device may indicate the first model to the terminal device via the local identifier of the first model.

[0207] It should be noted that in the above scenario, for the network device, the association relationship between the local identifier and the public identifier of the first model can be maintained. For the terminal device, the terminal device may not be aware of the above association relationship, or in other words, the association relationship may not be visible over the air interface. Of course, in the embodiment of the present application, the terminal device may also be aware of the above association relationship.

[0208] For another example, the terminal device can use the first model locally and associate the first model with the local identifier. Thereafter, during the use, management, and update of the first model, the terminal device can indicate the first model to the network device using the local identifier of the first model.

[0209] It should be noted that in the above scenario, for the terminal device, the association relationship between the local identifier and the public identifier of the first model can be maintained. For the network device, the network device may not be aware of the above association relationship, or in other words, the association relationship may not be visible over the air interface. Of course, in the embodiment of the present application, the network device may also be aware of the above association relationship.

[0210] For another example, if the network device wishes to transfer the first model to the terminal device for use, the network device may associate the first model with the local identifier and then indicate the first model to the terminal device via the local identifier associated with the first model.

[0211] It should be noted that in the above scenario, for the network device, the association relationship between the local identifier and the public identifier of the first model can be maintained. For the terminal device, the terminal device may not be aware of the above association relationship, or in other words, the association relationship may not be visible over the air interface. Of course, in the embodiment of the present application, the terminal device may also be aware of the above association relationship.

[0212] For another example, if the terminal device wishes to transfer the first model to the network device for use, the terminal device may associate the first model with the local identifier and then indicate the first model to the network device using the local identifier associated with the first model.

[0213] It should be noted that in the above scenario, for the network device, the association relationship between the local identifier and the public identifier of the first model can be maintained. For the terminal device, the terminal device may not be aware of the above association relationship, or in other words, the association relationship may not be visible over the air interface. Of course, in the embodiment of the present application, the terminal device may also be aware of the above association relationship.

[0214] For another example, the network device may directly indicate the first model to the terminal device through the local identifier. Accordingly, the terminal device may confirm the first model based on the local identifier and download the first model.

[0215] It should be noted that in the above scenario, for the terminal device, the terminal device needs to download the first model. Therefore, the terminal device needs to determine the public identifier of the first model based on the association relationship between the local identifier and the public identifier and the local identifier of the first model, and download the first model based on the public identifier of the first model. At this time, the association relationship is visible in the air. Of course, in the embodiment of the present application, if the terminal device can determine the first model only by the local identifier, the terminal device may not be aware of the above association relationship.

[0216] For another example, the terminal device may directly indicate the first model to the network device through the local identifier. Accordingly, the network device may confirm the first model based on the local identifier and download the first model.

[0217] It should be noted that in the above scenario, for the network device, the network device needs to download the first model. Therefore, the network device needs to determine the public identifier of the first model based on the association relationship between the local identifier and the public identifier and the local identifier of the first model, and download the first model based on the public identifier of the first model. At this time, the association relationship is visible in the air. Of course, in the embodiment of the present application, if the network device can determine the first model only by the local identifier, the network device may not be aware of the above association relationship.

[0218] In addition, in some implementations, in response to receiving the first information, the second device (e.g., a terminal device or a network device) can download the first model. The downloading can include online downloading or offline downloading. This embodiment of the present application is not limited to this.

[0219] As described above, embodiments of the present application may involve one or more of the following associations: an association between a local identifier and a model, an association between a local identifier and a public identifier, and an association between a public identifier and a model. In some scenarios, the above associations may need to be changed, or in other words, the above associations may need to be modified. Therefore, in order to unify the understanding of the above associations by the first device and the second device, the first device may indicate the change of the above association to the second device through third information.

[0220] That is, in some implementations, the above method also includes: the first device sends third information to the second device, and the third information is used to indicate one or more of the following: a change in the association relationship between the first local identifier and the first model; a change in the association relationship between the first local identifier and the first public identifier; and a change in the association relationship between the first public identifier and the first model.

[0221] It should be noted that, in the embodiment of the present application, the change of the above-mentioned association relationship may include one or more of the addition of an association relationship, the deletion of an association relationship, and the update of an association relationship, and the embodiment of the present application does not limit this.

[0222] In some implementations, for example, where the association relationship includes an association relationship between a local identifier and a model, the change in the association relationship may include changing the local ID corresponding to one or a group of models. For example, the local identifier corresponding to one or a group of models may be changed from local identifier 1 to local identifier 2.

[0223] In some implementations, for example, where the association relationship includes an association relationship between a public identifier and a local identifier, the change in the association relationship may include changing the public identifier corresponding to one or a group of models. For example, the public identifier corresponding to one or a group of local identifiers may be changed from public identifier 1 to public identifier 2.

[0224] In some implementations, for example, where the association relationship includes an association relationship between a public identifier and a local identifier, the change in the association relationship may include modifying the model corresponding to one or a group of local identifiers. For example, the model corresponding to one or a group of local identifiers may be changed from Model 1 to Model 2.

[0225] It should be noted that the embodiments of the present application do not limit the third information. In some implementations, the third information may be transmitted via signaling, where the signaling may include, for example, one or more of UCI, DCI, MAC CE, RRC signaling, RRC reconfiguration message, system broadcast, MIB, SIB1, and SIB. In other implementations, the third information may be transmitted as data, that is, the third information may be transmitted via a data channel, where the data channel may include, for example, one or more of PDSCH, PUSCH, and PSSCH.

[0226] In some scenarios, it may be necessary to delete the identifier associated with the model (e.g., the public identifier and / or the local identifier). Therefore, in order to unify the understanding of the above identifiers by the first device and the second device, the first device can indicate the deletion of the above identifier to the second device through the fourth information.

[0227] That is, the above method further includes the first device sending fourth information to the second device, where the fourth information is used to indicate one or more of the following: deletion of the first local identifier; and deletion of the first public identifier.

[0228] It should be noted that, in the embodiment of the present application, the model corresponding to the deleted identifier may no longer be used by the second device. Of course, in the embodiment of the present application, the model corresponding to the deleted identifier may no longer be used by the first device, or the model corresponding to the deleted identifier may be used by the first device. The embodiment of the present application does not limit this.

[0229] For example, the first device may send fourth information to the second device, where the fourth information is used to indicate that one or a group of local identifiers are deleted. Accordingly, after the second device deletes one or a group of local identifiers, the model associated with the one or a group of local identifiers is no longer used by the second device.

[0230] For another example, the first device may send fourth information to the second device, where the fourth information is used to indicate that one or a group of public identifiers are deleted. Accordingly, after the second device deletes one or a group of public identifiers, the model associated with the one or a group of public identifiers is no longer used by the first device and the second device.

[0231] It should be noted that the embodiments of the present application do not limit the fourth information. In some implementations, the fourth information may be transmitted via signaling, where the signaling may include, for example, one or more of UCI, DCI, MAC CE, RRC signaling, RRC reconfiguration message, system broadcast, MIB, SIB1, and SIB. In other implementations, the fourth information may be transmitted as data, that is, the fourth information may be transmitted via a data channel, where the data channel may include, for example, one or more of PDSCH, PUSCH, and PSSCH.

[0232] In some scenarios, it may be necessary to add identifiers associated with the model (e.g., public identifiers and / or local identifiers). Therefore, in order to unify the understanding of the above identifiers by the first device and the second device, the first device can indicate the addition of the above identifiers to the second device through the fifth information.

[0233] That is, the above method further includes the first device sending fifth information to the second device, where the fifth information is used to indicate one or more of the following: the addition of the first local identifier; and the addition of the first public identifier.

[0234] It should be noted that, in the embodiment of the present application, the model corresponding to the newly added identifier can be used by the second device. Of course, in the embodiment of the present application, the model corresponding to the newly added identifier can also be used by the first device, and the embodiment of the present application does not limit this.

[0235] For example, the first device can send fifth information to the second device, where the fifth information is used to indicate a newly added local identifier or a group of local identifiers, and a model associated with the newly added local identifier or a group of local identifiers. Accordingly, the second device stores the association relationship between the newly added local identifier or the group of local identifiers and the model.

[0236] For another example, the first device may send fifth information to the second device, where the fifth information is used to indicate a newly added local identifier or a group of local identifiers, and a public identifier associated with the newly added local identifier or a group of local identifiers. Accordingly, the second device stores the association relationship between the newly added local identifier or the group of local identifiers and the public identifier.

[0237] For another example, the first device may send fifth information to the second device, where the fifth information is used to indicate the addition of one or a group of public identifiers, and a model associated with the newly added one or a group of public identifiers. Accordingly, the second device stores the association relationship between the newly added one or a group of public identifiers and the model.

[0238] For another example, the first device may send fifth information to the second device, where the fifth information is used to indicate the addition of one or a group of public identifiers, and a local identifier associated with the newly added one or a group of public identifiers. Accordingly, the second device stores the association relationship between the newly added one or a group of public identifiers and the local identifier.

[0239] It should be noted that the embodiments of the present application do not limit the fifth information. In some implementations, the fifth information may be transmitted via signaling, where the signaling may include, for example, one or more of UCI, DCI, MAC CE, RRC signaling, RRC reconfiguration message, system broadcast, MIB, SIB1, and SIB. In other implementations, the fifth information may be transmitted as data, that is, the fifth information may be transmitted via a data channel, where the data channel may include, for example, one or more of PDSCH, PUSCH, and PSSCH.

[0240] The method embodiment of the present application is described in detail above in conjunction with Figures 1 to 12. The device embodiment of the present application is described in detail below in conjunction with Figures 13 to 15. 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.

[0241] FIG13 is a schematic diagram of a communication device according to an embodiment of the present application, wherein the communication device 1300 shown in FIG13 is a first device and includes a determining unit 1310 .

[0242] The determination unit 1310 is configured to determine first information, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; and a first local identifier associated with the first model and / or the first public identifier.

[0243] In some implementations, the first public identifier includes one or more of the following: a first identifier for identifying a usage scope of the first model; and a second identifier for identifying a model scheme of the first model.

[0244] In some implementations, the first identifier includes one or more of the following: a third identifier for identifying one or more regions; and a fourth identifier for identifying one or more institutions.

[0245] In some implementations, the third identifier includes regional identifiers of multiple regions ranging from large to small.

[0246] In some implementations, the fourth identifier is used to identify one or more of the following organizations: an organization that provides the first model; and an organization that optimizes the first model.

[0247] In some implementations, the second identifier includes one or more of the following: a fifth identifier for identifying a serial number of the first model; a sixth identifier for identifying a task of the first model; and a seventh identifier for identifying a characteristic attribute of the first model.

[0248] In some implementations, the seventh identifier includes one or more of the following identifiers: an eighth identifier associated with the model structure of the first model; a ninth identifier associated with the model platform of the first model; a tenth identifier associated with the interface of the first model; an eleventh identifier associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; a thirteenth identifier associated with the quantization method of the first model; a fourteenth identifier associated with the model complexity of the first model; and a fifteenth identifier associated with the size of the first model.

[0249] In some implementations, the first public identifier is used to uniquely identify the first model within a first scope.

[0250] In some implementations, the first scope includes one of: global, national, regional, and institutional.

[0251] In some implementations, the number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

[0252] In some implementations, the device further includes: a first sending unit, configured to send the first information to a second device.

[0253] In some implementations, the device further includes: a second sending unit, configured to send second information to a second device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

[0254] In some implementations, the device further includes: a third sending unit, configured to send third information to the second device, wherein the third information is configured to indicate one or more of: a change in the association relationship between the first local identifier and the first model; a change in the association relationship between the first local identifier and the first public identifier; and a change in the association relationship between the first public identifier and the first model.

[0255] In some implementations, the device further includes: a fourth sending unit, configured to send fourth information to the second device, wherein the fourth information is configured to indicate one or more of: deletion of the first local identifier; and deletion of the first public identifier.

[0256] In some implementations, the device further includes: a fifth sending unit, configured to send fifth information to the second device, wherein the fifth information is configured to indicate one or more of the following: a new addition of the first local identifier; a new addition of the first public identifier.

[0257] In some implementations, the association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

[0258] In some implementations, the first local identifier includes one or more of the following: a local identifier corresponding to an operator; a local identifier corresponding to a base station; a local identifier corresponding to a terminal device; and a local identifier corresponding to a region.

[0259] In some implementations, the first device and the second device satisfy one of the following: the first device is a terminal device, and the second device is a base station; the first device is a base station, and the second device is a terminal device; the first device is a terminal device, and the second device is a core network device; the first device is a core network device, and the second device is a terminal device; the first device is a base station, and the second device is a core network device; the first device is a core network device, and the second device is a base station; the first device and the second device are both terminal devices; the first device and the second device are both base stations; and the first device and the second device are both core network devices.

[0260] FIG14 is a schematic diagram of a communication device according to an embodiment of the present application. The communication device 1400 shown in FIG14 is a second device. The communication device 1400 may include a receiving unit 1410 .

[0261] The receiving unit 1410 is used to receive first information sent by a first device, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; a first local identifier associated with the first model and / or the first public identifier.

[0262] In some implementations, the first public identifier includes one or more of the following: a first identifier for identifying a usage scope of the first model; and a second identifier for identifying a model scheme of the first model.

[0263] In some implementations, the first identifier includes one or more of the following: a third identifier for identifying one or more regions; and a fourth identifier for identifying one or more institutions.

[0264] In some implementations, the third identifier includes regional identifiers of multiple regions ranging from large to small.

[0265] In some implementations, the fourth identifier is used to identify one or more of the following organizations: an organization that provides the first model; and an organization that optimizes the first model.

[0266] In some implementations, the second identifier includes one or more of the following: a fifth identifier for identifying a serial number of the first model; a sixth identifier for identifying a task of the first model; and a seventh identifier for identifying a characteristic attribute of the first model.

[0267] In some implementations, the seventh identifier includes one or more of the following identifiers: an eighth identifier associated with the model structure of the first model; a ninth identifier associated with the model platform of the first model; a tenth identifier associated with the interface of the first model; an eleventh identifier associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; a thirteenth identifier associated with the quantization method of the first model; a fourteenth identifier associated with the model complexity of the first model; and a fifteenth identifier associated with the size of the first model.

[0268] In some implementations, the first public identifier is used to uniquely identify the first model within a first scope.

[0269] In some implementations, the first scope includes one of: global, national, regional, and institutional.

[0270] In some implementations, the number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

[0271] In some implementations, the receiving unit is configured to receive second information sent by the first device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

[0272] In some implementations, the receiving unit is used to receive third information sent by the first device, and the third information is used to indicate one or more of the following: a change in the association relationship between the first local identifier and the first model; a change in the association relationship between the first local identifier and the first public identifier; and a change in the association relationship between the first public identifier and the first model.

[0273] In some implementations, the receiving unit is configured to receive fourth information sent by the first device, where the fourth information is configured to indicate one or more of: deletion of the first local identifier; and deletion of the first public identifier.

[0274] In some implementations, the receiving unit is used to receive fifth information sent by the first device, where the fifth information is used to indicate one or more of the following: a new addition of the first local identifier; or a new addition of the first public identifier.

[0275] In some implementations, the association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

[0276] In some implementations, the first local identifier includes one or more of the following: a local identifier corresponding to an operator; a local identifier corresponding to a base station; a local identifier corresponding to a terminal device; and a local identifier corresponding to a region.

[0277] In some implementations, the first device and the second device satisfy one of the following: the first device is a terminal device, and the second device is a base station; the first device is a base station, and the second device is a terminal device; the first device is a terminal device, and the second device is a core network device; the first device is a core network device, and the second device is a terminal device; the first device is a base station, and the second device is a core network device; the first device is a core network device, and the second device is a base station; the first device and the second device are both terminal devices; the first device and the second device are both base stations; and the first device and the second device are both core network devices.

[0278] FIG15 is a schematic diagram of the structure of an apparatus according to an embodiment of the present application. The dotted lines in FIG15 indicate that the unit or module is optional. Apparatus 1500 may be used to implement the method described in the above method embodiment. Apparatus 1500 may be a chip or a terminal device.

[0279] The device 1500 may include one or more processors 1510. The processor 1510 may support the device 1500 to implement the method described in the method embodiment above. The processor 1510 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.

[0280] The apparatus 1500 may further include one or more memories 1520. The memories 1520 store programs that can be executed by the processor 1510, causing the processor 1510 to perform the methods described in the above method embodiments. The memories 1520 may be independent of the processor 1510 or integrated into the processor 1510.

[0281] The apparatus 1500 may further include a transceiver 1530. The processor 1510 may communicate with other devices or chips via the transceiver 1530. For example, the processor 1510 may transmit and receive data with other devices or chips via the transceiver 1530.

[0282] The present invention also provides a computer-readable storage medium for storing a program. The computer-readable storage medium can be applied to a terminal device provided in the present invention, and the program enables a computer to execute the method performed by the terminal device in each embodiment of the present invention.

[0283] The present application also provides a computer program product. The computer program product includes a program. The computer program product can be applied to the terminal device provided in the present application, and the program causes a computer to execute the method performed by the terminal device in each embodiment of the present application.

[0284] The embodiments of the present application also provide a computer program. The computer program can be applied to the terminal device provided in the embodiments of the present application, and the computer program enables a computer to execute the method executed by the terminal device in each embodiment of the present application.

[0285] 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.

[0286] 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.

[0287] 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.

[0288] 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.

[0289] 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.

[0290] 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.

[0291] 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.

[0292] 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.

[0293] 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.

[0294] 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.

[0295] 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.

[0296] 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)).

[0297] 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 wireless communication method, characterized in that: include: The first device determines first information, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; A first local identifier is associated with the first model and / or the first public identifier.

2. The method according to claim 1, characterized in that The first public identifier includes one or more of the following: A first identifier, used to identify the scope of use of the first model; and The second identifier is used to identify the model scheme of the first model.

3. The method according to claim 2, characterized in that The first identifier includes one or more of the following: A third identifier is used to identify one or more regions; and The fourth identifier is used to identify one or more organizations.

4. The method according to claim 3, characterized in that The third identifier includes regional identifiers of multiple regions with a geographical range from large to small.

5. The method according to claim 3 or 4, characterized in that The fourth identifier is used to identify one or more of the following organizations: providing a mechanism for said first model; and Optimize the structure of the first model.

6. The method according to any one of claims 2 to 5, characterized in that The second identifier includes one or more of the following: A fifth identifier, used to identify the serial number of the first model; a sixth identifier, used to identify the task of the first model; as well as The seventh identifier is used to identify the characteristic attributes of the first model.

7. The method according to claim 6, characterized in that The seventh identifier includes one or more of the following identifiers: an eighth identifier, associated with the model structure of the first model; a ninth identifier, associated with the model platform of the first model; a tenth identifier, associated with the interface of the first model; an eleventh identifier, associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; A thirteenth identifier is associated with the quantization method of the first model; A fourteenth identifier is associated with the model complexity of the first model; as well as The fifteenth identifier is associated with the size of the first model.

8. The method according to any one of claims 1 to 7, characterized in that The first public identifier is used to uniquely identify the first model within a first scope.

9. The method according to claim 8, characterized in that The first scope includes one of the following: global, national, regional and institutional.

10. The method according to any one of claims 1 to 9, characterized in that The number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

11. The method according to any one of claims 1 to 10, characterized in that The method further comprises: The first device sends the first information to the second device.

12. The method according to any one of claims 1 to 11, characterized in that The method further comprises: The first device sends second information to the second device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

13. The method according to any one of claims 1 to 12, characterized in that The method further comprises: The first device sends third information to the second device, where the third information is used to indicate one or more of the following: a change in the association between the first local identifier and the first model; a change in the association between the first local identifier and the first public identifier; and A change in the association relationship between the first public identifier and the first model.

14. The method according to any one of claims 1 to 12, characterized in that The method further comprises: The first device sends fourth information to the second device, where the fourth information is used to indicate one or more of the following: Deletion of the first local identifier; and Deletion of the first public identifier.

15. The method according to any one of claims 1 to 12, characterized in that The method further comprises: The first device sends fifth information to the second device, where the fifth information is used to indicate one or more of the following: Addition of the first local identifier; The first public identification is newly added.

16. The method according to any one of claims 1 to 15, characterized in that The association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

17. The method according to any one of claims 1 to 16, characterized in that The first local identifier includes one or more of the following: The local identifier of the operator; The local identifier corresponding to the base station; The local identifier of the terminal device; and The local identifier corresponding to the region.

18. The method according to any one of claims 1 to 17, characterized in that The first device and the second device meet one of the following requirements: The first device is a terminal device, and the second device is a base station; The first device is a base station, and the second device is a terminal device; The first device is a terminal device, and the second device is a core network device; The first device is a core network device, and the second device is a terminal device; The first device is a base station, and the second device is a core network device; The first device is a core network device, and the second device is a base station; The first device and the second device are both terminal devices; The first device and the second device are both base stations; and The first device and the second device are both core network devices.

19. A wireless communication method, characterized in that: include: The second device receives first information sent by the first device, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; A first local identifier is associated with the first model and / or the first public identifier.

20. The method according to claim 19, characterized in that The first public identifier includes one or more of the following: A first identifier, used to identify the scope of use of the first model; and The second identifier is used to identify the model scheme of the first model.

21. The method according to claim 20, characterized in that The first identifier includes one or more of the following: A third identifier is used to identify one or more regions; and The fourth identifier is used to identify one or more organizations.

22. The method according to claim 21, characterized in that The third identifier includes regional identifiers of multiple regions with a geographical range from large to small.

23. The method according to claim 21 or 22, characterized in that The fourth identifier is used to identify one or more of the following organizations: providing a mechanism for said first model; and Optimize the structure of the first model.

24. The method according to any one of claims 20 to 23, characterized in that The second identifier includes one or more of the following: A fifth identifier, used to identify the serial number of the first model; a sixth identifier, used to identify the task of the first model; as well as The seventh identifier is used to identify the characteristic attributes of the first model.

25. The method according to claim 24, characterized in that The seventh identifier includes one or more of the following identifiers: an eighth identifier, associated with the model structure of the first model; a ninth identifier, associated with the model platform of the first model; a tenth identifier, associated with the interface of the first model; an eleventh identifier, associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; A thirteenth identifier is associated with the quantization method of the first model; A fourteenth identifier is associated with the model complexity of the first model; as well as The fifteenth identifier is associated with the size of the first model.

26. The method according to any one of claims 19 to 25, characterized in that The first public identifier is used to uniquely identify the first model within a first scope.

27. The method according to claim 26, characterized in that The first scope includes one of the following: global, national, regional and institutional.

28. The method according to any one of claims 19 to 27, characterized in that The number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

29. The method according to any one of claims 19 to 28, wherein: The method further comprises: The second device receives second information sent by the first device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

30. The method according to any one of claims 19 to 29, wherein: The method further comprises: The second device receives third information sent by the first device, where the third information is used to indicate one or more of the following: a change in the association between the first local identifier and the first model; a change in the association between the first local identifier and the first public identifier; and A change in the association relationship between the first public identifier and the first model.

31. The method according to any one of claims 19 to 29, wherein: The method further comprises: The second device receives fourth information sent by the first device, where the fourth information is used to indicate one or more of the following: Deletion of the first local identifier; and Deletion of the first public identifier.

32. The method according to any one of claims 19 to 29, wherein: The method further comprises: The second device receives fifth information sent by the first device, where the fifth information is used to indicate one or more of the following: Addition of the first local identifier; The first public identification is newly added.

33. The method according to any one of claims 19 to 32, wherein: The association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

34. The method according to any one of claims 19 to 33, wherein: The first local identifier includes one or more of the following: The local identifier of the operator; The local identifier corresponding to the base station; The local identifier of the terminal device; and The local identifier corresponding to the region.

35. The method according to any one of claims 19 to 34, wherein: The first device and the second device meet one of the following requirements: The first device is a terminal device, and the second device is a base station; The first device is a base station, and the second device is a terminal device; The first device is a terminal device, and the second device is a core network device; The first device is a core network device, and the second device is a terminal device; The first device is a base station, and the second device is a core network device; The first device is a core network device, and the second device is a base station; The first device and the second device are both terminal devices; The first device and the second device are both base stations; and The first device and the second device are both core network devices.

36. A communication device, characterized in that: The communication device is a first device, comprising: A determining unit is configured to determine first information, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; A first local identifier is associated with the first model and / or the first public identifier.

37. The device according to claim 36, characterized in that The first public identifier includes one or more of the following: A first identifier, used to identify the scope of use of the first model; and The second identifier is used to identify the model scheme of the first model.

38. The apparatus according to claim 37, wherein The first identifier includes one or more of the following: A third identifier is used to identify one or more regions; and The fourth identifier is used to identify one or more organizations.

39. The device according to claim 38, characterized in that The third identifier includes regional identifiers of multiple regions with a geographical range from large to small.

40. The apparatus according to claim 38 or 39, characterized in that The fourth identifier is used to identify one or more of the following organizations: providing a mechanism for said first model; and Optimize the structure of the first model.

41. The apparatus according to any one of claims 37 to 40, characterized in that The second identifier includes one or more of the following: A fifth identifier, used to identify the serial number of the first model; a sixth identifier, used to identify the task of the first model; as well as The seventh identifier is used to identify the characteristic attributes of the first model.

42. The device according to claim 41, characterized in that The seventh identifier includes one or more of the following identifiers: an eighth identifier, associated with the model structure of the first model; a ninth identifier, associated with the model platform of the first model; a tenth identifier, associated with the interface of the first model; an eleventh identifier, associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; A thirteenth identifier is associated with the quantization method of the first model; A fourteenth identifier is associated with the model complexity of the first model; as well as The fifteenth identifier is associated with the size of the first model.

43. The apparatus according to any one of claims 36 to 42, characterized in that The first public identifier is used to uniquely identify the first model within a first scope.

44. The apparatus according to claim 8, wherein The first scope includes one of the following: global, national, regional and institutional.

45. The apparatus according to any one of claims 36 to 44, characterized in that The number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

46. ​​The apparatus according to any one of claims 36 to 45, characterized in that The device further comprises: The first sending unit is configured to send the first information to the second device.

47. The apparatus according to any one of claims 36 to 46, characterized in that The device further comprises: The second sending unit is configured to send second information to a second device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

48. The apparatus according to any one of claims 36 to 47, characterized in that The device further comprises: A third sending unit is configured to send third information to the second device, where the third information is used to indicate one or more of the following: a change in the association between the first local identifier and the first model; a change in the association between the first local identifier and the first public identifier; and A change in the association relationship between the first public identifier and the first model.

49. The apparatus according to any one of claims 36 to 47, characterized in that The device further comprises: A fourth sending unit is configured to send fourth information to the second device, where the fourth information is used to indicate one or more of the following: Deletion of the first local identifier; and Deletion of the first public identifier.

50. The apparatus according to any one of claims 36 to 47, characterized in that The device further comprises: A fifth sending unit is configured to send fifth information to the second device, where the fifth information is used to indicate one or more of the following: Addition of the first local identifier; The first public identification is newly added.

51. The apparatus according to any one of claims 36 to 50, characterized in that The association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

52. The apparatus according to any one of claims 36 to 51, characterized in that The first local identifier includes one or more of the following: The local identifier of the operator; The local identifier corresponding to the base station; The local identifier of the terminal device; and The local identifier corresponding to the region.

53. The apparatus according to any one of claims 36 to 52, characterized in that The first device and the second device meet one of the following requirements: The first device is a terminal device, and the second device is a base station; The first device is a base station, and the second device is a terminal device; The first device is a terminal device, and the second device is a core network device; The first device is a core network device, and the second device is a terminal device; The first device is a base station, and the second device is a core network device; The first device is a core network device, and the second device is a base station; The first device and the second device are both terminal devices; The first device and the second device are both base stations; and The first device and the second device are both core network devices.

54. A communication device, characterized in that The communication device is a second device, including: A receiving unit, configured to receive first information sent by a first device, where the first information includes one or more of the following: a first public identifier associated with a first model for wireless communication; A first local identifier is associated with the first model and / or the first public identifier.

55. The apparatus according to claim 54, wherein The first public identifier includes one or more of the following: A first identifier, used to identify the scope of use of the first model; and The second identifier is used to identify the model scheme of the first model.

56. The apparatus according to claim 55, wherein The first identifier includes one or more of the following: A third identifier is used to identify one or more regions; and The fourth identifier is used to identify one or more organizations.

57. The apparatus according to claim 56, wherein The third identifier includes regional identifiers of multiple regions with a geographical range from large to small.

58. The apparatus according to claim 56 or 57, characterized in that The fourth identifier is used to identify one or more of the following organizations: providing a mechanism for said first model; and Optimize the structure of the first model.

59. The apparatus according to any one of claims 55 to 58, characterized in that The second identifier includes one or more of the following: A fifth identifier, used to identify the serial number of the first model; a sixth identifier, used to identify the task of the first model; as well as The seventh identifier is used to identify the characteristic attributes of the first model.

60. The apparatus according to claim 59, wherein The seventh identifier includes one or more of the following identifiers: an eighth identifier, associated with the model structure of the first model; a ninth identifier, associated with the model platform of the first model; a tenth identifier, associated with the interface of the first model; an eleventh identifier, associated with the performance of the first model; a twelfth identifier associated with the training data of the first model; A thirteenth identifier is associated with the quantization method of the first model; A fourteenth identifier is associated with the model complexity of the first model; as well as The fifteenth identifier is associated with the size of the first model.

61. The apparatus according to any one of claims 54 to 60, characterized in that The first public identifier is used to uniquely identify the first model within a first scope.

62. The device according to claim 61, characterized in that The first scope includes one of the following: global, national, regional and institutional.

63. The apparatus according to any one of claims 54 to 62, characterized in that The number of bits occupied by the first local identifier is smaller than the number of bits occupied by the first public identifier.

64. The apparatus according to any one of claims 54 to 63, characterized in that The receiving unit is configured to receive second information sent by the first device, where the second information is used to indicate an association relationship between the first public identifier and the first local identifier.

65. The apparatus according to any one of claims 54 to 64, characterized in that The receiving unit is configured to receive third information sent by the first device, where the third information is used to indicate one or more of the following: a change in the association between the first local identifier and the first model; a change in the association between the first local identifier and the first public identifier; and A change in the association relationship between the first public identifier and the first model.

66. The apparatus according to any one of claims 54 to 64, characterized in that The receiving unit is configured to receive fourth information sent by the first device, where the fourth information is used to indicate one or more of the following: Deletion of the first local identifier; and Deletion of the first public identifier.

67. The apparatus according to any one of claims 54 to 64, characterized in that The receiving unit is configured to receive fifth information sent by the first device, where the fifth information is used to indicate one or more of the following: the addition of the first local identifier; The first public identification is newly added.

68. The apparatus according to any one of claims 54 to 67, characterized in that The association relationship between the first local identifier and the first public identifier is configured by the first device or the second device.

69. The apparatus according to any one of claims 54 to 68, characterized in that The first local identifier includes one or more of the following: The local identifier of the operator; The local identifier corresponding to the base station; The local identifier of the terminal device; and The local identifier corresponding to the region.

70. The apparatus according to any one of claims 54 to 69, characterized in that The first device and the second device meet one of the following requirements: The first device is a terminal device, and the second device is a base station; The first device is a base station, and the second device is a terminal device; The first device is a terminal device, and the second device is a core network device; The first device is a core network device, and the second device is a terminal device; The first device is a base station, and the second device is a core network device; The first device is a core network device, and the second device is a base station; The first device and the second device are both terminal devices; The first device and the second device are both base stations; and The first device and the second device are both core network devices.

71. A communication device, characterized in that The terminal comprises a transceiver, a memory and a processor, wherein the memory is used to store a program, and the processor is used to call the program in the memory and control the transceiver to receive or send a signal so that the terminal executes the method as described in any one of claims 1 to 35.

72. A device, characterized in that The device comprises a processor configured to call a program from a memory so as to cause the device to execute the method according to any one of claims 1 to 35.

73. A chip, characterized in that: The device comprises a processor configured to call a program from a memory so that a device equipped with the chip executes the method according to any one of claims 1 to 35.

74. A computer-readable storage medium, characterized in that A program is stored thereon, the program causing a computer to execute the method according to any one of claims 1 to 35.

75. A computer program product, characterized in that The method comprises a program for causing a computer to execute the method according to any one of claims 1 to 35.

76. A computer program, characterized in that The computer program causes a computer to execute the method according to any one of claims 1 to 35.

Images