Transmission method and apparatus, and first device and second device

Abstract

The present application belongs to the technical field of communications. Disclosed are a transmission method and apparatus, and a first device and a second device. The transmission method in the embodiments of the present application comprises: a first device acquiring first information, wherein the first information is information obtained on the basis of an AI model; and on the basis of the first information, the first device performing first transmission, wherein the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode; and the first information includes at least one of the following: a first transmission mode; at least one piece of spatial-domain information; at least one piece of first performance information, which is performance information related to transmission in the full-duplex transmission mode; at least one first transmission parameter, which is a transmission parameter for uplink transmission; at least one second transmission parameter, which is a transmission parameter for downlink transmission; a resource of at least one guard band; a parameter related to at least one uplink transmit power; and at least one piece of interference information.

Description

Transmission method, apparatus, first device and second device

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority from the Chinese patent application No. 202411344905.0 filed on September 25, 2024, and entitled "Transmission method, apparatus, first device and second device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application belongs to the field of communication technology, and particularly relates to a transmission method, apparatus, first device and second device. BACKGROUND

[0004] In order to improve the delay and coverage performance of a Time Division Duplexing (TDD) system, full-duplex transmission is introduced, that is, a network-side device or a terminal can use a full-duplex transmission mode for transmission. When the network-side device or the terminal uses the full-duplex transmission mode for transmission, the received signal is interfered by the transmitted signal. However, the existing interference suppression method and transmission method can easily lead to low resource utilization and reduced performance. Therefore, the introduction of full-duplex transmission can easily lead to a decline in transmission performance in the related art. SUMMARY

[0005] Embodiments of the present application provide a transmission method, apparatus, first device and second device, which can determine a transmission mode or a transmission-related parameter based on an AI model in the case of introducing full-duplex transmission, so as to facilitate guaranteeing transmission performance.

[0006] In a first aspect, a transmission method is provided, and the method comprises:

[0007] A first device obtains first information, wherein the first information is information obtained based on an Artificial Intelligent (AI) model;

[0008] The first device performs first transmission based on the first information, wherein a transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode;

[0009] The first information comprises at least one of the following:

[0010] The first transmission mode comprises a half-duplex transmission mode or a full-duplex transmission mode;

[0011] At least one spatial domain information;

[0012] at least one first performance information, the first performance information being performance information related to transmission in a full duplex transmission mode;

[0013] at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission;

[0014] at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission;

[0015] at least one guard band resource;

[0016] at least one uplink transmit power related parameter;

[0017] at least one interference information.

[0018] In a second aspect, a transmission apparatus is provided, and the apparatus comprises:

[0019] a processing module configured to obtain first information, the first information being information obtained based on an artificial intelligence (AI) model;

[0020] a transceiving module configured to perform first transmission based on the first information, the first transmission corresponding to a half duplex transmission mode or a full duplex transmission mode;

[0021] The first information comprises at least one of the following:

[0022] a first transmission mode, the first transmission mode comprising a half duplex transmission mode or a full duplex transmission mode;

[0023] at least one spatial domain information;

[0024] at least one first performance information, the first performance information being performance information related to transmission in a full duplex transmission mode;

[0025] at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission;

[0026] at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission;

[0027] at least one guard band resource;

[0028] at least one uplink transmit power related parameter;

[0029] at least one interference information.

[0030] In a third aspect, a transmission method is provided, and the method comprises:

[0031] a second device performing a second operation, the second operation comprising at least one of the following:

[0032] obtain first information based on the AI model, and send the first information to the first device;

[0033] receive second information from the first device, the second information including at least one of the following: the first information, at least part of the input information of the AI model;

[0034] train at least part of the AI model;

[0035] send model information, the model information being used to determine at least part of the AI model;

[0036] send a supervision result of the AI model;

[0037] send indication information for triggering AI model training;

[0038] send indication information for triggering AI model inference;

[0039] wherein the AI model is used to predict at least one of the following:

[0040] a first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0041] at least one spatial domain information;

[0042] at least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode;

[0043] at least one first transmission parameter, the first transmission parameter being a transmission parameter for uplink transmission;

[0044] at least one second transmission parameter, the second transmission parameter being a transmission parameter for downlink transmission;

[0045] at least one resource of a guard band;

[0046] at least one related parameter of uplink transmit power;

[0047] at least one interference information.

[0048] In a fourth aspect, a transmission apparatus is provided, the apparatus comprising:

[0049] a processing module configured to perform a second operation, the second operation including at least one of the following:

[0050] obtain first information based on the AI model, and send the first information to the first device;

[0051] receiving second information from the first device, the second information comprising at least one of: the first information, at least part of the input information of the AI model;

[0052] training at least part of the AI model;

[0053] sending model information, the model information being used to determine at least part of the AI model;

[0054] sending a supervision result of the AI model;

[0055] sending indication information for triggering AI model training;

[0056] sending indication information for triggering AI model inference;

[0057] wherein the AI model is used to predict at least one of:

[0058] a first transmission mode, the first transmission mode comprising a half-duplex transmission mode or a full-duplex transmission mode;

[0059] at least one spatial domain information;

[0060] at least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode;

[0061] at least one first transmission parameter, the first transmission parameter being a transmission parameter for uplink transmission;

[0062] at least one second transmission parameter, the second transmission parameter being a transmission parameter for downlink transmission;

[0063] at least one resource of a guard band;

[0064] at least one related parameter of uplink transmit power;

[0065] at least one interference information.

[0066] In a fifth aspect, a device for transmission is provided, the device being configured to perform the steps of the method according to the first aspect, or to implement the steps of the method according to the third aspect.

[0067] In a sixth aspect, a first device is provided, the first device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method according to the first aspect.

[0068] In a seventh aspect, a first device is provided, including a processor and a communication interface, wherein the processor is configured to obtain first information, the first information being information obtained based on an artificial intelligence (AI) model; and the communication interface is configured to perform first transmission based on the first information, the first transmission corresponding to a half-duplex transmission mode or a full-duplex transmission mode.

[0069] The first information includes at least one of the following:

[0070] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0071] At least one spatial domain information.

[0072] At least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode.

[0073] At least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission.

[0074] At least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission.

[0075] At least one resource of a guard band.

[0076] At least one related parameter of uplink transmission power.

[0077] At least one interference information.

[0078] In an eighth aspect, a second device is provided, including a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions being executed by the processor to implement the steps of the method according to the third aspect.

[0079] In a ninth aspect, a second device is provided, including a processor and a communication interface, wherein the processor is configured to perform a second operation, the second operation including at least one of the following:

[0080] Obtaining first information based on an AI model and sending the first information to a first device.

[0081] Receiving second information from the first device, the second information including at least one of the following: the first information, at least part of input information of the AI model.

[0082] Training at least part of the AI model.

[0083] Sending model information, the model information being used to determine at least part of the AI model.

[0084] sending a supervision result of the AI model;

[0085] sending indication information for triggering AI model training;

[0086] sending indication information for triggering AI model inference;

[0087] The AI model is used to predict at least one of the following:

[0088] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0089] At least one spatial domain information;

[0090] At least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode;

[0091] At least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission;

[0092] At least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission;

[0093] At least one resource of a guard band;

[0094] At least one related parameter of uplink transmit power;

[0095] At least one interference information.

[0096] In a tenth aspect, a readable storage medium is provided, the readable storage medium storing a program or instructions, the program or instructions being executed by a processor to implement steps of the method according to the first aspect, or to implement steps of the method according to the third aspect.

[0097] In an eleventh aspect, a wireless communication system is provided, including a first device and a second device, the first device being configured to implement steps of the transmission method according to the first aspect, and the second device being configured to implement steps of the transmission method according to the third aspect.

[0098] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to run a program or instructions to implement steps of the method according to the first aspect, or to implement steps of the method according to the third aspect.

[0099] In a thirteenth aspect, a computer program / program product is provided, the computer program / program product being stored in a storage medium, the computer program / program product being executed by at least one processor to implement steps of the method according to the first aspect, or to implement steps of the method according to the third aspect.

[0100] In the embodiments of the present application, the first device obtains first information, the first information being information obtained based on an AI model; and performs first transmission based on the first information, the first transmission corresponding to a half-duplex transmission mode or a full-duplex transmission mode; wherein the first information includes at least one of the following: a first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode; at least one spatial domain information; at least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode; at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission; at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission; at least one resource of a guard band; at least one related parameter of uplink transmission power; and at least one interference information. That is, in the embodiments of the present application, the transmission mode or the transmission related parameter is obtained based on an AI model to perform transmission, which is beneficial to guarantee transmission performance. BRIEF DESCRIPTION OF DRAWINGS

[0101] FIG. 1 is a block diagram of a wireless communication system to which embodiments of the present application can be applied;

[0102] FIG. 2a is a schematic diagram of a neural network according to an embodiment of the present application;

[0103] FIG. 2b is a schematic diagram of a neuron according to an embodiment of the present application;

[0104] FIG. 3 is a schematic diagram of a framework of AI lifecycle management according to an embodiment of the present application;

[0105] FIG. 4a to FIG. 4d are schematic diagrams of full-duplex transmission according to embodiments of the present application;

[0106] FIG. 5 is a flowchart of Rel-15 NR Uu CSI acquisition according to an embodiment of the present application;

[0107] FIG. 6 is a flowchart of a transmission method according to an embodiment of the present application;

[0108] FIG. 7 is a flowchart of another transmission method according to an embodiment of the present application;

[0109] FIG. 8 is a structural diagram of a transmission apparatus according to an embodiment of the present application;

[0110] FIG. 9 is a structural diagram of another transmission apparatus according to an embodiment of the present application;

[0111] FIG. 10 is a structural diagram of a communication device according to an embodiment of the present application;

[0112] FIG. 11 is a structural diagram of a terminal according to an embodiment of the present application;

[0113] FIG. 12 is a structural diagram of a network-side device according to an embodiment of the present application. DETAILED DESCRIPTION

[0114] The technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all the other embodiments obtained by those of ordinary skill in the art belong to the scope of protection of the present application.

[0115] The terms "first", "second", and the like in the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein, and the objects distinguished by "first", "second" are generally a category and do not limit the number of objects, for example, the first object can be one or more. In addition, "or" in the present application means at least one of the connected objects. For example, the protection scope of "A or B" at least covers three schemes, namely, scheme one: including A and not including B; scheme two: including B and not including A; scheme three: including A and including B. In addition, the terms "A and / or B", "at least one of A and B", "at least one of A or B" also at least cover the above three schemes, respectively. The character " / " generally represents that the objects before and after are in an "or" relationship.

[0116] The term "indication" in the present application can be a direct indication (or explicit indication) or an indirect indication (or implicit indication). The direct indication can be understood as that the sender explicitly informs the receiver of the specific information, the operation to be performed or the request result, etc. in the indication sent by the sender. The indirect indication can be understood as that the receiver determines the corresponding information according to the indication sent by the sender, or judges and determines the operation to be performed or the request result, etc. according to the judgment result.

[0117] It is worth noting that the technology described in the embodiments of the present application is not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA) or other systems. The terms "system" and "network" in the embodiments of the present application are often used interchangeably, and the described technology can be used in the above-mentioned systems and radio technologies, as well as in other systems and radio technologies. The following description describes a New Radio (NR) system for example purposes, and NR terminology is used in most of the following description, but these technologies can also be applied to systems other than NR systems, such as 6th Generation (6G) communication systems. th

[0118] ​FIG. 1 shows a block diagram of a wireless communication system to which embodiments of the present application can be applied. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a terminal-side device such as a mobile phone, a Tablet Personal Computer, a Laptop Computer, a notebook computer, a Personal Digital Assistant (PDA), a palmtop computer, a netbook, an Ultra-mobile Personal Computer (UMPC), a Mobile Internet Device (MID), an Augmented Reality (AR) device, a Virtual Reality (VR) device, a robot, a wearable device, a flight vehicle, a Vehicle User Equipment (VUE), a shipboard device, a Pedestrian User Equipment (PUE), a smart home (a home device with a wireless communication function such as a refrigerator, a television, a washing machine, or furniture), a game console, a Personal Computer (PC), a kiosk, or a self-service machine. The wearable device includes a smart watch, a smart bracelet, a smart earphone, smart glasses, smart jewelry (a smart bracelet, a smart necklace, a smart ring, a smart necklace, a smart anklet, a smart necklace, etc.), a smart wristband, smart clothes, etc. The vehicle-mounted device can also be referred to as a vehicle-mounted terminal, a vehicle-mounted controller, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit, etc. It should be noted that the specific type of the terminal 11 is not limited in the embodiments of the present application. The network-side device 12 can include an access network device or a core network device. The access network device can also be referred to as a Radio Access Network (RAN) device, a radio access network function, or a radio access network unit. The access network device can include a base station, a Wireless Local Area Network (WLAN) Access Point (AP), or a Wireless Fidelity (WiFi) node, etc.The base station can be referred to as a Node B (NB), an evolved Node B (eNB), a next generation Node B (gNB), a New Radio Node B (NR Node B), an access point, a relay station (RBS), a serving base station (SBS), a base transceiver station (BTS), a radio base station, a radio transceiver, a basic service set (BSS), an extended service set (ESS), a home Node B (HNB), a home evolved Node B, a transmit / receive point (TRP), or some other suitable terminology in the art, and is not limited to a particular technical terminology, provided that the same technical effect is achieved. It should be noted that in the embodiments of the present application, only the base station in the NR system is taken as an example for introduction, and the specific type of the base station is not limited.

[0119] The core network device can also be referred to as a core network node, a core network function, or a core network network element, etc., which includes but is not limited to at least one of the following: a mobility management entity (MME), an access and mobility management function (AMF), a session management function (SMF), a user plane function (UPF), a policy control function (PCF), a policy and charging rules function (PCRF), an edge application server discovery function (EASDF), a unified data management (UDM), a unified data repository (UDR), a home subscriber server (HSS), a centralized network configuration (CNC), a network repository function (NRF), a network exposure function (NEF), a local NEF (L-NEF), a binding support function (BSF), an application function (AF), a location management function (LMF), a gateway mobile location center (GMLC), a network data analytics function (NWDAF), etc. It should be noted that only the core network device in the NR system is taken as an example for introduction in the embodiments of the present application, and the specific type of the core network device is not limited. If the name of the core network device mentioned in the embodiments of the present application changes in the subsequent protocol version (for example, 6G), it is also within the protection scope of the present application.

[0120] Optionally, the core network device can be implemented by one or more function modules in one device, or can be implemented by multiple devices together, and the embodiments of the present application do not make specific limitations thereto. It can be understood that the function module can be a network element in a hardware device, a software function module running on a special hardware, or a virtualized function module instantiated on a platform (for example, a cloud platform).

[0121] For the convenience of understanding, some contents related to the embodiments of the present application are described as follows:

[0122] I. Artificial Intelligence (AI) / Machine Learning (ML)

[0123] Artificial intelligence has been widely applied in various fields. It is an important task for future wireless communication networks to integrate artificial intelligence into wireless communication networks to significantly improve technical indicators such as throughput, delay, and user capacity. There are various implementation methods for AI modules, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. The present application takes neural networks as an example for illustration, but does not limit the specific types of AI modules.

[0124] Exemplarily, a neural network can be as shown in FIG. 2a, and the neural network is composed of neurons, each of which can be as shown in FIG. 2b. Wherein a1, a2, … aK are inputs, w is a weight (multiplicative coefficient), b is a bias (additive coefficient), and σ(.) is an activation function. Common activation functions include Sigmoid, tanh, Rectified Linear Unit (ReLU), etc.

[0125] The parameters of the neural network are optimized by a gradient optimization algorithm. Gradient optimization algorithm is a class of algorithms for minimizing or maximizing an objective function (also known as loss function), and the objective function is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). After obtaining the model, we can get the predicted output f(x) according to the input x, and can calculate the difference between the predicted value and the true value (f(x)-Y), which is the loss function. The goal is to find appropriate W and b to minimize the value of the loss function, where the smaller the loss value, the closer the model is to the true situation.

[0126] The common optimization algorithm is basically based on error back propagation (BP) algorithm. The basic idea of BP algorithm is that the learning process consists of two processes of forward propagation of signals and backward propagation of errors. When forward propagation, the input sample is transmitted from the input layer to the output layer through the processing of each hidden layer. If the actual output of the output layer does not match the expected output, the backward propagation of error is entered. Error back propagation is to transmit the output error to the input layer through the hidden layer in a certain form, and allocate the error to all units of each layer, so as to obtain the error signal of each unit, which is used as the basis for correcting the weight of each unit. The weight adjustment process of each layer of the signal forward propagation and the error backward propagation is repeated. The process of continuously adjusting the weight is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or the learning time reaches the preset learning time.

[0127] The common optimization algorithm includes gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (the name of the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square prop (RMSprop), adaptive moment estimation (Adam), etc.

[0128] These optimization algorithms, when error back propagation, are based on the error / loss obtained from the loss function, and the derivative / partial derivative of the current neuron is added to the learning rate, the previous gradient / derivative / partial derivative, etc. to obtain the gradient, and the gradient is transmitted to the previous layer.

[0129] Generally speaking, according to the type of problem to be solved, the selected AI algorithm and the adopted AI model also have some differences. The main method of improving the performance of 5G network by means of AI is to enhance or replace the existing algorithm or processing module by means of neural network-based algorithm and AI model. In a specific scenario, neural network-based algorithm and AI model can achieve better performance than deterministic algorithm. Commonly used neural networks include deep neural network, convolutional neural network and recurrent neural network, etc. With the existing AI tools, the construction, training and verification of neural network can be realized.

[0130] II. Fine-tuning

[0131] In practice, it is difficult to achieve convergence by directly training a neural network due to the insufficient size of the real-time collected dataset. A common approach is to pre-train the network based on a large amount of offline collected data to achieve convergence. Then, fine-tune the pre-trained neural network parameters with real-time collected data to adapt the neural network to the actual environment. Fine-tuning can be considered as a training process that uses the pre-trained neural network parameters as initialization. In the fine-tuning stage, the parameters of some layers can be frozen, usually the layers close to the input end are frozen, and the layers close to the output end are activated, which can ensure that the network can still converge. The less the amount of data in the fine-tuning stage, the more layers are recommended to be frozen, and only a small number of layers close to the output end are fine-tuned.

[0132] III. Generalization of neural networks

[0133] Generalization refers to the ability of a neural network to produce reasonable outputs for data encountered outside the training or learning process. To address the generalization problem caused by the variability of wireless transmission environments, there are two solutions for neural network-based wireless communication systems. The first solution is to train different neural networks under different transmission conditions, obtain multiple sets of neural network parameters, and switch the neural network parameters as the actual environment changes. The second solution is to train a common neural network based on mixed data, and the neural network parameters do not need to be switched with the change of the environment. These two modes have their own advantages and disadvantages: the first solution performs well under different transmission conditions, but requires storing multiple network parameters and switching them as needed, which can cause signaling overhead and frequent switching problems; the second solution only needs to store a set of neural network parameters and does not need to switch, but cannot achieve optimal performance under each transmission condition. The way of constructing mixed datasets will affect the performance of the second solution.

[0134] IV. Label

[0135] In machine learning and deep learning, a label typically refers to the identification or annotation of the true class or target value of a data sample. The label is used to represent the information that the model should learn and predict. The following examples are used to illustrate:

[0136] Label in classification tasks: In classification tasks, the label represents which class a data sample belongs to. For example, in image classification, each image sample has a label representing the class of the object or scene contained in the image, such as "dog" or "cat".

[0137] Labels in object detection: In object detection tasks, labels typically include both location information (e.g., bounding boxes of objects) and class information. Each label identifies one target object in an image, including its location and class. Labels in regression tasks:

[0138] In regression tasks, labels typically represent continuous or real-valued targets to be predicted. For example, the label in a house price prediction task can be the actual sale price of a house.

[0139] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are often used for tasks such as part-of-speech tagging, named entity recognition, etc., where labels are used to represent the properties or categories of each word or character in a text sequence.

[0140] Labels are a key component in supervised learning tasks, used to train machine learning models. Models learn patterns and rules through comparison with true labels in order to make predictions or classifications on unseen data. The quality and accuracy of labels are crucial for the performance of models.

[0141] Five, AI life cycle management (LCM)

[0142] The life cycle management of AI / ML models includes multiple AI function modules: model training, model deployment, model inference, model monitoring, model updating. Exemplarily, the specific framework of AI life cycle management can be as shown in FIG. 3.

[0143] (1) Model training

[0144] Perform AI model training, validation and testing, which can generate model performance indicators that can be used as part of the model testing process. If necessary, this function is also responsible for data preparation based on the training data provided by the data collection function, such as data preprocessing and cleaning, formatting and conversion.

[0145] Train / update model: If there is a model storage function, it is used to transfer the AI model that has been trained, validated and tested to the model storage function, or to transfer the updated version of the model to the model storage function.

[0146] (2) Model management

[0147] Supervise AI models or operations of issued AI functions, such as model selection / activation / deactivation / switching / fallback, and feedback model monitoring performance. This module is also responsible for making decisions based on data received from the data collection module and the inference module to ensure correct inference operations.

[0148] Management instructions: Information input by the model management function to the model inference function. Relevant information can include AI model or AI / ML-based function to select / disable / activate / switch models / fallback to non-AI / ML operation (i.e. not dependent on inference process) etc.

[0149] Model transfer request: Request for a model to the model storage function.

[0150] Performance feedback / retraining request: Information required by the model training function as input, for example for model (re)training or update purposes.

[0151] (3) Model inference

[0152] Using data provided by the data collection function as input (i.e. inference data), the inference function provides the output of applying the AI model. If necessary, the inference function is also responsible for data preparation (e.g. data pre-processing and cleaning, formatting and conversion) based on the inference data provided by the data collection function.

[0153] Inference output: Data used by the management function to monitor the performance of the AI model or AI / ML function.

[0154] Six, Full Duplex (Full Duplex) mode

[0155] In the 5G mobile communication system, in order to adapt to the diversified scene and business demand, the full duplex is enhanced technology. The main scenarios of 5G include enhanced mobile broadband (Enhance Mobile Broadband, eMBB), ultra-reliable and low latency communication (Ultra-Reliable and Low Latency Communications, URLLC), massive machine type of communication (massive Machine Type of Communication, mMTC), these scenarios put forward high reliability, low latency, large bandwidth, wide coverage and other requirements to the system.

[0156] In NR, configuring full duplex operation can significantly improve the latency and coverage performance of time division duplex (Time Division Duplexing, TDD) systems.

[0157] Sub-band non-overlapping full duplex (subbands non-overlapping Full duplex) can improve transmission delay and enhance coverage.

[0158] For a downlink (DL) slot (configured by tdd-UL-DL-ConfigurationCommon, or tdd-UL-DL-ConfigurationDedicated), the network configures a DL bandwidth part (BWP) for the UE, and for an uplink (UL) slot, the network configures a UL BWP for the UE. For example, slot 1 and slot 4.

[0159] Referring to FIG. 4a, for a full duplex scenario, there are the following cases:

[0160] Case 1: DL BWP is configured, i.e., slot 1;

[0161] Case 2: DL BWP and UL sub band are configured, i.e., slot 2.

[0162] Referring to FIG. 4b, for a UL slot (configured by tdd-UL-DL-ConfigurationCommon, or tdd-UL-DL-ConfigurationDedicated), there are the following cases:

[0163] Case 3: UL BWP is configured, i.e., slot 4;

[0164] Case 4: UL BWP and DL sub band are configured, i.e., slot 5.

[0165] For a seamless bidirectional forwarding detection (SBFD) operation, an SBFD sub band is composed of one resource block (RB) or one set of contiguous RBs with the same transmission direction.

[0166] A time unit (e.g., slot or symbol) in which a gNB uses an SBFD operation can be referred to as an SBFD time unit (e.g., slot or symbol).

[0167] Referring to FIG. 4c, for Rel-15, a base station and a UE can only transmit or receive at one time. For a Rel-18 gNB full duplex, a gNB can simultaneously transmit and receive, and a UE can only use a half duplex mode, i.e., can only transmit or receive at one time. For a UE full duplex, a gNB and a UE can simultaneously transmit and receive.

[0168] For UE-side full duplex, a larger guard bandwidth (GB) (larger than the GB of base station frequency division (FD)) can be needed to suppress self-interference, see FIG. 4d.

[0169] For a communication device, simultaneous UL reception and DL transmission can cause self-interference. To ensure transmission in the interfered direction, the communication device needs to have self-interference cancellation capability, such as reserving a guard band between the reception band and the transmission band, but this can reduce the throughput of the UE.

[0170] It should be further noted that in the related art, certain interference isolation or interference cancellation measures are usually adopted to suppress interference, for example, interference isolation can increase the number of antennas for isolation through the antennas; or increase the frequency domain guard band for frequency domain isolation. Interference cancellation needs to estimate or reproduce the interference signal, which can introduce additional devices and is easily affected by the environment, temperature, etc., resulting in inaccurate estimation of the interference signal. Interference isolation needs to reserve more resources for the frequency domain guard band, which can result in low resource utilization. In addition, in order to ensure the performance of reception, it can be necessary to adopt a way to reduce the transmission power, which can result in a decline in transmission performance.

[0171] In 5G and future 6G systems, both base stations and terminals can adopt full duplex mode.

[0172] Seven, about Quasi-Co-Location (QCL)

[0173] The description of the physical downlink control channel (PDCCH), the physical downlink shared channel (PDSCH), and the synchronization signal block (SSB) / channel state information reference signal (CSI-RS) quasi co-location in the embodiments of the present application and the description of the demodulation reference signal (DMRS) or DMRS antenna port of the PDCCH and the PDSCH quasi co-location with the SSB / CSI-RS have the same meaning; or it can be understood that the quasi co-location properties between the two are the same.

[0174] Transmission Configuration Indication (TCI) state refers to that the network indicates that the DMRS antenna ports of PDCCH, PDSCH or PDCCH, PDSCH are quasi co-located with a certain downlink reference signal (RS) (for example, SSB / CSI-RS).

[0175] The properties of quasi co-location include at least one of the following: Doppler shift, Doppler spread, average delay, delay spread, spatial RX parameters.

[0176] Eight, about multi-antenna

[0177] Wireless access technology standards such as Long Term Evolution (LTE) / LTE-Advanced (LTE-A) are built based on Multiple-Input Multiple-Output (MIMO) and Orthogonal Frequency Division Multiplexing (OFDM) technologies. Among them, the MIMO technology uses the spatial degrees of freedom that can be obtained by a multi-antenna system to improve the peak rate and system spectral efficiency.

[0178] The dimension of MIMO technology is constantly expanding in the process of standardization development. In the eighth release (Release 8, Rel-8) of LTE, up to 4 layers of MIMO transmission can be supported. In the ninth release (Release 9, Rel-9), the multi-user MIMO (MU-MIMO) technology is enhanced, and up to 4 downlink data layers can be supported in the MU-MIMO transmission of transmission mode (TM)-8. In the tenth release (Release 10, Rel-10), the transmission capacity of single-user MIMO (SU-MIMO) is expanded to up to 8 data layers.

[0179] The industry is further promoting MIMO technology towards three-dimension and large-scale. Currently, 3GPP has completed the research project of three-dimension (3D) channel modeling, and is carrying out research and standardization work of enhanced full dimension MIMO (eFD-MIMO) and NR MIMO. It can be foreseen that in the future 5G mobile communication system, MIMO technology with larger scale and more antenna ports will be introduced.

[0180] Massive MIMO technology uses a large-scale antenna array, which can greatly improve the system frequency band utilization efficiency and support a larger number of access users. Therefore, massive MIMO technology is regarded by various research organizations as one of the most potential physical layer technologies in the next generation mobile communication system.

[0181] In the massive MIMO technology, if a full digital array is used, the maximum spatial resolution and optimal MU-MIMO performance can be achieved, but such a structure requires a large number of analog-to-digital (AD) / digital-to-analog (DA) conversion devices and a large number of complete radio frequency-baseband processing channels, which will be a huge burden on both device cost and baseband processing complexity.

[0182] In order to avoid the implementation cost and device complexity, a digital-analog hybrid beamforming technology emerges, that is, on the basis of traditional digital domain beamforming, an additional beamforming is added to the radio frequency signal near the front end of the antenna system. The analog beamforming can make the transmitted signal and the channel achieve rough matching through a relatively simple way. The dimension of the equivalent channel formed after analog beamforming is less than the actual number of antennas, so the required AD / DA converter, the number of digital channels and the corresponding baseband processing complexity can be greatly reduced. The residual interference of the analog beamforming part can be processed again in the digital domain, so as to ensure the quality of MU-MIMO transmission. Compared with full digital beamforming, the digital-analog hybrid beamforming is a compromise between performance and complexity, and has a high practical prospect in the system with high frequency band, large bandwidth or large number of antennas.

[0183] Nine, about high frequency band

[0184] In the research of the next generation communication system after 4G, the working frequency band supported by the system is raised to above 6GHz, and the highest is about 100GHz. High frequency band has more abundant idle frequency resources, which can provide more throughput for data transmission. Currently, 3GPP has completed the high frequency channel modeling work. The wavelength of high frequency signal is short, compared with low frequency band, more antenna elements can be arranged on the same size panel, and the beamforming technology is used to form beams with stronger directivity and narrower lobes. Therefore, it is also one of the future trends to combine large-scale antenna with high frequency communication.

[0185] X. Beam measurement and reporting

[0186] Analog beamforming is full-bandwidth transmission, and each polarization direction element on each high-frequency antenna array panel can only transmit analog beams in a time-division multiplexing manner. The analog beamforming weights are realized by adjusting the parameters of the radio frequency front-end phase shifter and other devices.

[0187] Currently, in the academic and industrial circles, the training of analog beamforming vectors is usually carried out in a polling manner, that is, the elements of each polarization direction of each antenna panel transmit training signals (i.e. candidate beamforming vectors) in a time-division multiplexing manner in turn at the appointed time, and the terminal feeds back the beam report after measurement, which is used by the network side to realize analog beam transmission when transmitting services next time. The content of the beam report usually includes the optimal number of transmission beam identifiers and the measured received power of each transmission beam.

[0188] When doing beam measurement, the network configures the configuration information of beam report, in which the reference signal resource setting (RS resource setting) is associated, and the reference signal resource setting includes at least one reference signal resource set, and each reference signal resource set includes at least one reference signal resource, such as SSB resource or CSI-RS resource. The UE measures the Layer 1 Reference Signal Receiving Power (L1-RSRP) / Layer 1 Signal to Interference Plus Noise Ratio (L1-SINR) of each RS resource, and reports the optimal at least one measurement result to the network, including SSB Rank Indicator (RI) or Channel State Information Reference Signal Resource Indicator (CRI), and L1-RSRP / L1-SINR.

[0189] In the configuration information of the beam report, it is indicated whether the report is a group-based beam report. If it is a non-group-based beam report, the UE reports at least one optimal beam and its quality for the network to determine the beam used to send a channel or a signal to the UE. If it is a group-based beam report, the UE reports a pair of beams and their quality, and the UE can receive simultaneously when the network uses the pair of beams to send information to the UE.

[0190] Eleven, beam alignment

[0191] The following is an example of downlink beam alignment. The beam alignment is roughly divided into two stages. The first stage is to preliminarily train the initial transmission beam from the base station to the UE when the UE accesses the network. The second stage is to train the fine transmission and reception beam pair from the base station to the UE after the UE establishes a connection. The beam training in the second stage is mainly completed through CSI measurement and feedback.

[0192] For the first stage, the base station periodically transmits SSBs and transmits a set of SSBs in a beam sweeping manner in each SSB transmission period. The UE measures the reference signal carried by the SSB and reports the index of the SSB with higher received energy to the base station to determine the transmission beam of the base station. The UE reports the SSB index according to the rules specified in the protocol, and each SSB corresponds to a set of physical random access channel (PRACH) resources. The UE transmits the initial access preamble on the corresponding PRACH resource to represent the corresponding SSB index reported by the UE. For the second stage, the fifteenth version (Release 15, Rel-15) NR Uu channel state information (CSI) acquisition process is shown in FIG. 5. The base station configures the CSI reporting parameters and triggers the CSI reporting. The UE performs CSI measurement and reporting according to the base station configuration information, and the base station adjusts the transmission parameters such as uplink and downlink beams according to the UE reporting results. Each CSI reporting configuration indicates the type of CSI reporting (CSI quantity), including parameters such as CRI, SSB index indicating beams, and other parameter types such as precoding matrix indicator (PMI), RI, CQI, L1, RSRP, SINR, i1, etc.

[0193] For uplink beam training, the base station configures a sounding reference signal (SRS) resource for the UE to perform uplink beam training. The UE autonomously transmits SRS on the corresponding SRS resource to perform beam training.

[0194] In addition, for base station / UE-side beam training, the base station / UE can autonomously select the training beam.

[0195] Twelfth, beam indication

[0196] For uplink beam indication, the base station indicates the beam direction used by the UE on the UL scheduling resource, and the beam direction is represented by SRS resource indicator (SRI). For downlink beam indication, the base station indicates the beam direction on the DL scheduling resource so that the UE can determine its receiving beam. The downlink beam direction is indicated by the associated TCI, which reflects information such as CRI, SSB index, etc.

[0197] It should be noted that the AI model of the embodiments of the present application can also be referred to as an AI unit, a machine learning (ML) model, an ML unit, an AI structure, an AI function, an AI feature, a machine learning model, a neural network, a neural network function, a neural network function, etc., or the AI unit can also refer to a processing unit capable of implementing a specific algorithm, formula, processing flow, capability, etc. related to AI, or the AI unit can be a processing method, algorithm, function, module or unit for a specific data set, or the AI unit can be a processing method, algorithm, function, module or unit running on AI / ML related hardware such as GPU, NPU, TPU, ASIC, etc. The embodiments of the present application do not make specific limitations. Optionally, the specific data set includes at least one of the input and output of the AI unit.

[0198] Optionally, the identifier (i.e. ID) of the AI model can be an AI model identifier, an AI structure identifier, an AI algorithm identifier, or an identifier of a specific data set associated with the AI unit, or an identifier of a specific scene, environment, channel feature, device related to AI / ML, or an identifier of a function, feature, capability or module related to AI / ML. The embodiments of the present application do not make specific limitations.

[0199] Optionally, the index of the AI model can be described in various ways, such as functionality ID (functionality ID) and / or model ID (model ID), model physical ID, model logical ID, model global ID, and model local ID.

[0200] In addition, AI in the embodiments of the present application can also represent machine learning, which has various implementation methods, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of the present application do not make specific limitations.

[0201] It should also be noted that the cell (cell) involved in the embodiments of the present application can be replaced by a cell group (cell group), a frequency layer (frequency layer), a tracking area (Tracking Area, TA), a TRP, a network node, a carrier (carrier), a bandwidth (band), a sub-band (subband) or a bandwidth part (Bandwidth Part, BWP), etc. In addition, the first cell involved in the embodiments of the present application can include at least one of the following: a source cell, a target cell, a currently camped cell, a currently accessed cell, a primary cell (Primary Cell, PCell), a secondary cell (Secondary Cell, SCell).

[0202] The SSB and the SS / PBCH block involved in the embodiments of the present application can be used interchangeably, or can also be called other names, that is, can refer to any module containing at least part of the synchronization signal, broadcast signal or other downlink broadcast signal or control channel thereof.

[0203] The server involved in the embodiments of the present application can be a device for training or prediction or providing AI-related information, or can be a third server, or can be a device provided by an over-the-top (OTT) service provider or a third-party service provider or the Internet.

[0204] The transmission method provided by the embodiments of the present application will be described in detail in combination with the accompanying drawings, some embodiments and application scenarios.

[0205] Please refer to FIG. 6, which is a flowchart of a transmission method provided by the embodiments of the present application. The method can be executed by a first device, as shown in FIG. 6, and includes the following steps:

[0206] Step 601: The first device acquires first information, which is information obtained based on an AI model.

[0207] Step 602: The first device performs first transmission based on the first information. The transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode.

[0208] The first information includes at least one of the following:

[0209] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0210] At least one spatial domain information.

[0211] At least one first performance information, which is performance information related to transmission in a full-duplex transmission mode.

[0212] At least one first transmission parameter, which is a transmission parameter for uplink transmission.

[0213] At least one second transmission parameter, which is a transmission parameter for downlink transmission.

[0214] At least one resource of a guard band.

[0215] At least one related parameter of uplink transmission power.

[0216] At least one interference information.

[0217] In this embodiment, the first device can include a terminal or a network side device, etc. The first information is information obtained based on an AI model. For example, the first device can obtain the first information based on the inference of the AI model, or the first device can receive the first information from the second device. For example, the second device obtains the first information based on the inference of the AI model, and sends the first information to the first device. The second device can include a terminal, a network side device, a server, etc. It can be understood that, in the case that the first device and the second device are both terminals, the first device and the second device are different terminals; in the case that the first device and the second device are both network side devices, the first device and the second device are different network side devices.

[0218] The full duplex transmission mode can include an enhanced duplex mode, a sub-band full duplex mode, etc. In some optional embodiments, the first transmission mode can include a transmission mode under at least one spatial domain information, or the first transmission mode can include a transmission mode under at least one signal quality strength (for example, Reference Signal Receiving Power, RSRP) range.

[0219] The spatial domain information can include but is not limited to at least one of the following: Transmission Configuration Indication (TCI), beam information, reference signal information (for example, reference signal index), QCL, spatial information, spatial characteristics, antenna panel, TRP, etc. The reference signal can include at least one of SSB, CSI-RS and SRS, etc.

[0220] It also needs to be explained that the spatial domain information can also be represented as spatial characteristics, beam, QCL, QCL source spatial attribute, spatial domain characteristics, TCI, TCI state, TRP, RS, SSB, panel, etc.

[0221] The first performance information can be performance information related to transmission under the full duplex transmission mode, for example, at least one of the number of transmissions under the full duplex transmission mode, the probability of successful transmission under the full duplex transmission mode, the probability of failed transmission under the full duplex transmission mode, the number of failed transmissions under the full duplex transmission mode, etc. In some optional embodiments, the first performance information can include performance information under at least one spatial domain information, or the first performance information can include performance information under at least one signal quality strength (for example, RSRP) range, or performance information within a time period.

[0222] The first transmission parameter can include, but is not limited to, at least one of a resource corresponding to the uplink transmission, a transmission number, and a retransmission number. It should be noted that the first transmission parameter can correspond to a full-duplex transmission mode, that is, the first transmission parameter is a transmission parameter of the uplink transmission in the full-duplex transmission mode. Exemplarily, the uplink transmission can include, but is not limited to, a PRACH, a physical uplink control channel (PUCCH), a dynamic grant (DG) physical uplink shared channel (PUSCH), a configured grant (CG) PUSCH, a sounding reference signal (SRS), and the like.

[0223] In some optional embodiments, the first transmission parameter can include a transmission parameter of the uplink transmission in at least one spatial domain information, or the first transmission parameter can include a transmission parameter of the uplink transmission in at least one RSRP range.

[0224] The second transmission parameter can include, but is not limited to, at least one of a resource corresponding to the downlink transmission, a transmission number, and a retransmission number. It should be noted that the second transmission parameter can correspond to a full-duplex transmission mode, that is, the second transmission parameter is a transmission parameter of the downlink transmission in the full-duplex transmission mode. In some optional embodiments, the second transmission parameter can include a transmission parameter of the downlink transmission in at least one spatial domain information, or the second transmission parameter can include a transmission parameter of the downlink transmission in at least one RSRP range.

[0225] Exemplarily, the downlink transmission can include, but is not limited to, an SSB, a CSI-RS, a physical downlink control channel (PDCCH), a DG physical downlink shared channel (PDSCH), a semi-persistent scheduling (SPS) PDSCH, a positioning reference signal (PRS), and the like.

[0226] The resource of the guard band (GB) can include a location, a length, a size, and the like of the guard band. In some optional embodiments, the resource of the guard band can include a guard band resource under at least one spatial domain information, or the resource of the guard band can include a guard band resource under at least one signal quality strength (for example, RSRP) range, or can include a guard band resource corresponding to at least one uplink transmission power.

[0227] The related parameter of the uplink transmission power can include, but is not limited to, at least one of a target uplink transmission power, a target received power value, a maximum transmission power, a power boosting value, a power backoff value, and the like. In some optional embodiments, the related parameter of the uplink transmission power can include an uplink transmission power related parameter under at least one spatial domain information, or the related parameter of the uplink transmission power can include an uplink transmission power related parameter under at least one signal quality strength (for example, RSRP) range.

[0228] It should be noted that, in the case of predicting the related parameter of the transmission power based on the AI model, the input information of the AI model can include interference information, first device power, first device type, and the like.

[0229] The interference information can include, but is not limited to, at least one of self-interference information, mutual interference information, interference cancellation information, and the like. For example, the self-interference information can include a self-interference size or a self-interference strength, the mutual interference information can include a mutual interference size or a mutual interference strength, and the interference cancellation information can include interference signal information, for example, can include self-interference signal information. In some optional embodiments, in the case of ordering the interference sizes in descending order, the interference information can only include at least one of interference information with the interference size in the first N1 and interference information with the interference size in the last N2, where N1 and N2 are positive integers.

[0230] In some optional embodiments, in the case that the interference information only includes self-interference information, the inference based on the AI model can be performed by the first device side.

[0231] Exemplarily, the transmission parameters for full-duplex transmission, such as transmission resources of uplink and downlink, space information, related parameters of uplink transmission power, resources of guard band, and the like, can be obtained based on the AI model in the case that the first device needs to perform full-duplex transmission, which is beneficial to obtain more suitable transmission parameters for full-duplex transmission, and then perform full-duplex transmission based on the obtained transmission parameters for full-duplex transmission, which is beneficial to improve transmission performance; or the transmission mode can be obtained based on the AI model in the case that the first device needs to perform transmission, which is beneficial to obtain a more suitable transmission mode, and then perform transmission by using the obtained transmission mode, which is beneficial to improve transmission performance. In some optional embodiments, in the case that the transmission mode is obtained based on the AI model, the transmission parameters under the transmission mode can also be obtained based on the AI model, and then transmission can be performed by using the obtained transmission mode and parameters.

[0232] In some optional embodiments, the first information can also be referred to as full-duplex transmission information.

[0233] It should be noted that the first device performing the first transmission based on the first information can include that the first device directly performs the first transmission based on the first information, for example, in the case that the first information includes at least one of the first transmission parameter and the second transmission parameter, the first device can directly perform the first transmission based on the first information; or the first device can determine target information based on the first information, and perform the first transmission based on the target information, for example, in the case that the first information includes at least one space information, at least one first performance information, and the like, the first device can determine the transmission mode, transmission resources, and the like based on the first information, and perform the first transmission based on the determined transmission mode, transmission resources, and the like.

[0234] The embodiments of the present application are described below in combination with examples:

[0235] Exemplarily, the first transmission mode is obtained based on the AI model in this embodiment, so that the first device can select a corresponding transmission mode to perform transmission according to the first transmission mode, which can improve the performance of uplink and downlink transmission and improve system performance.

[0236] Exemplarily, the space information is obtained based on the AI model in this embodiment, so that the first device can select a corresponding uplink transmission resource or downlink transmission resource to perform transmission according to the space information, the direction corresponding to the space information can reduce self-interference between uplink and downlink, or reduce mutual interference between uplink and downlink transmission between different users, thereby improving the success rate of full-duplex transmission, and reducing retransmission after full-duplex failure caused by interference, and reducing power consumption of the first device.

[0237] Exemplarily, the embodiment obtains performance information related to transmission in the full-duplex transmission mode, i.e., the first performance information, based on the AI model, so that the first device can select a suitable transmission mode or transmission resource according to the first performance information, which is conducive to improving the success rate and transmission performance of the full-duplex transmission.

[0238] Exemplarily, the embodiment obtains the transmission parameter of the uplink transmission (i.e., the first transmission parameter) and the transmission parameter of the downlink transmission (i.e., the second transmission parameter), such as the resource of the uplink transmission and the resource of the downlink transmission, based on the AI model, so that the first device can directly perform the full-duplex transmission based on the transmission parameter of the uplink transmission and the transmission parameter of the downlink transmission, thereby simplifying the process of selecting the uplink transmission parameter and the downlink transmission parameter and improving the efficiency of the full-duplex transmission.

[0239] Exemplarily, the embodiment obtains the resource of the guard band based on the AI model, which is conducive to reducing the self-interference between the uplink and the downlink or the mutual interference between the uplink transmission and the downlink transmission of different users, thereby improving the performance of the full-duplex transmission and reducing the resource overhead caused by the guard band.

[0240] Exemplarily, the embodiment obtains the related parameter of the uplink transmission power based on the AI model, which is conducive to reducing the self-interference between the uplink and the downlink or the mutual interference between the uplink transmission and the downlink transmission of different users, thereby ensuring the performance of the uplink transmission in the full-duplex transmission and improving the performance of the downlink reception.

[0241] Exemplarily, the embodiment obtains the interference information based on the AI model, which can be used to suppress or cancel the self-interference between the uplink and the downlink or the mutual interference between the uplink transmission and the downlink transmission of different users, thereby improving the performance of the full-duplex transmission.

[0242] In summary, in the embodiment of the present application, the first device obtains first information, the first information being information obtained based on an AI model; and performs first transmission based on the first information, the transmission mode corresponding to the first transmission being a half-duplex transmission mode or a full-duplex transmission mode; wherein the first information includes at least one of the following: the first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode; at least one spatial domain information; at least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode; at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission; at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission; at least one resource of a guard band; at least one related parameter of uplink transmission power; and at least one interference information. That is, the embodiment of the present application obtains transmission mode or transmission related parameters based on an AI model to perform transmission, which is conducive to ensuring transmission performance.

[0243] Optionally, the first device obtains the first information, including:

[0244] The first device receives the first information from the second device.

[0245] Or,

[0246] The first device obtains the first information based on the AI model.

[0247] In some embodiments, the first information can be obtained by the second device based on the AI model, and the obtained first information is sent to the first device. Since AI inference often has higher requirements on device performance or computing power, AI inference by the second device can help reduce the performance requirements on the first device, or can save the computing power resources of the first device.

[0248] For example, in the case of the first device being a terminal, the terminal can receive the first information from a network side device or a server, and perform the first transmission according to the first information, which can help reduce the performance requirements on the terminal, or can save the computing power resources of the terminal; in the case of the first device being a network side device, the network side device can receive the first information from a server, and perform the first transmission according to the first information, which can help reduce the performance requirements on the network side device, or can save the computing power resources of the network side device.

[0249] In other embodiments, the first information can be obtained by the first device based on the AI model, and the first transmission is performed based on the obtained first information. Since the AI inference needs to be performed by the device that uses the first information for transmission, not only the transmission delay can be reduced, but also the resource overhead of the first information transmission can be saved.

[0250] Optionally, the spatial domain information includes at least one of the following: spatial domain information corresponding to the downlink transmission, and spatial domain information corresponding to the uplink transmission.

[0251] The spatial domain information corresponding to the downlink transmission can include, but is not limited to, at least one of the following information: TCI, SSB, CSI-RS, and beam corresponding to the uplink transmission. The spatial domain information corresponding to the uplink transmission can include, but is not limited to, at least one of the following information: TCI, SSB, CSI-RS, and beam corresponding to the uplink transmission.

[0252] For example, the spatial domain information corresponding to the downlink transmission can be used only for downlink transmission (i.e., DL only); the spatial domain information corresponding to the downlink transmission can be used only for uplink transmission (i.e., UL only).

[0253] Optionally, the first performance information includes at least one of the following:

[0254] The probability of successful transmission in the full-duplex transmission mode;

[0255] a probability of a transmission failure in a full-duplex transmission mode;

[0256] a number of transmission failures in a full-duplex transmission mode.

[0257] Optionally, the first transmission parameter comprises at least one of: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, a number of retransmissions.

[0258] Or,

[0259] The second transmission parameter comprises at least one of: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, a number of retransmissions.

[0260] Exemplarily, the time domain resource can comprise at least one of: a slot, a symbol, a subframe, etc. The frequency domain resource can comprise at least one of: a BWP, a subband, a resource block (RB), a resource block set, a carrier, etc. The spatial domain resource can comprise at least one of: a TCI state, an SSB, a CSI-RS, a QCL, a beam, etc.

[0261] It can be understood that the time domain resource, the frequency domain resource, the spatial domain resource, the number of transmissions or the number of retransmissions comprised in the first transmission parameter respectively represent the frequency domain resource, the spatial domain resource, the number of transmissions or the number of retransmissions corresponding to the uplink transmission; and the time domain resource, the frequency domain resource, the spatial domain resource, the number of transmissions or the number of retransmissions comprised in the second transmission parameter respectively represent the frequency domain resource, the spatial domain resource, the number of transmissions or the number of retransmissions corresponding to the downlink transmission.

[0262] Optionally, the resource of the guard band comprises at least one of: a frequency domain position of the guard band, a frequency domain size of the guard band.

[0263] Exemplarily, the frequency domain position of the guard band can comprise at least one of: a start position and an end position of the guard band. The frequency domain size of the guard band can comprise a length of the guard band or a number of frequency domain units, etc.

[0264] Optionally, the related parameter of the uplink transmit power comprises at least one of: a target uplink transmit power, a target receive power value, a maximum transmit power, a power boosting value, a power backoff value.

[0265] Optionally, the interference information comprises at least one of: interference intensity information, interference signal information.

[0266] Exemplarily, the interference intensity information can comprise an interference size, for example, a self-interference or inter-interference size in a specific resource, or a self-interference or inter-interference size in a specific uplink transmission power or uplink transmission power range; or a self-interference or inter-interference size in a specific beam or QCL. The interference signal information can be used to reduce or eliminate the interference information.

[0267] Optionally, the interference intensity information comprises at least one of the following: a self-interference intensity, an inter-interference intensity, and indication information indicating whether the interference intensity satisfies a corresponding threshold.

[0268] Exemplarily, the self-interference intensity can comprise at least one of the following: a self-interference intensity in a specific resource, a self-interference intensity in a specific uplink transmission power or uplink transmission power range, and a self-interference intensity in a specific beam or QCL. The inter-interference intensity can comprise at least one of the following: an inter-interference intensity in a specific resource, an inter-interference intensity in a specific uplink transmission power or uplink transmission power range, and an inter-interference intensity in a specific beam or QCL.

[0269] The interference intensity satisfying the corresponding threshold can comprise the interference intensity being higher than the corresponding threshold, or the interference intensity being less than or equal to the corresponding threshold. Exemplarily, the indication information indicating whether the interference intensity satisfies the corresponding threshold can comprise at least one of the following: indication information indicating whether the self-interference intensity satisfies the corresponding threshold, and indication information indicating whether the inter-interference intensity satisfies the corresponding threshold. It should be noted that the threshold corresponding to the self-interference intensity and the threshold corresponding to the inter-interference intensity can be the same or different.

[0270] Optionally, the interference signal information comprises at least one of the following: a reverse signal of at least one transmitted signal, and pre-processing information corresponding to the at least one transmitted signal.

[0271] The transmitted signal can be understood as a transmitted signal transmitted by the first device.

[0272] Exemplarily, the pre-processing information can comprise a pre-distortion amount, used to offset the interference.

[0273] Optionally, the first information further comprises at least one probability information.

[0274] The probability information corresponds to at least one of the following: at least one spatial domain information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one resource of a guard band, and at least one related parameter of an uplink transmission power.

[0275] That is, the first information can further include at least one of the following: probability information corresponding to the at least one spatial domain information, probability information corresponding to the at least one transmission mode, probability information corresponding to the at least one first transmission parameter, probability information corresponding to the at least one second transmission parameter, probability information corresponding to the at least one guard band resource, and probability information corresponding to the at least one uplink transmission power related parameter.

[0276] For example, the probability information corresponding to each spatial domain information can be used to indicate a probability of transmission using the spatial domain information. The probability information corresponding to each transmission mode can be used to indicate a probability of transmission using the transmission mode. The probability information corresponding to each first transmission parameter can be used to indicate a probability of uplink transmission using the first transmission parameter. The probability information corresponding to each second transmission parameter can be used to indicate a probability of downlink transmission using the second transmission parameter. The probability information corresponding to each guard band resource can be used to indicate a probability of transmission using the guard band resource. The probability information corresponding to each uplink transmission power related parameter can be used to indicate a probability of transmission using the uplink transmission power related parameter.

[0277] It should be noted that the at least one transmission mode, the at least one spatial domain information, the at least one first transmission parameter, the at least one second transmission parameter, the at least one guard band resource, and the at least one uplink transmission power related parameter corresponding to the probability information can be the same as the corresponding parameters included in the first information, or can include the corresponding parameters included in the first information, or can be different from the corresponding parameters included in the first information.

[0278] In this embodiment, the first information further includes at least one probability information, which is beneficial for the first device to select more suitable parameters for transmission according to the probability information.

[0279] The following examples are given in the following scenarios:

[0280] Scenario 1: A network-side device (e.g., a base station, a TRP, or a core network device, etc.) can obtain transmission information (i.e., first information) of a specific terminal, a group of terminals, a specific area, a specific beam direction, a specific reference signal, a specific reference point, a specific path loss or RSRP range, a specific transmission mode, a specific frequency domain resource, a specific uplink transmission power, a specific guard band, etc. based on an AI model, and notify the corresponding terminal, so that the terminal can directly or indirectly use the transmission information for transmission.

[0281] Scenario 2: A terminal can obtain transmission information or specific interference information (i.e., first information) between the terminal and at least one network-side device (e.g., a base station, a TRP, or a core network device, etc.) based on an AI model, where the transmission information is transmission information of a specific beam direction, a specific reference signal, a specific reference point, a specific path loss or RSRP range, a specific transmission mode, a specific frequency domain resource, a specific uplink transmission power, a specific guard band, etc., so that the terminal can directly or indirectly use the transmission information or interference information for transmission.

[0282] Exemplarily, the first information can include at least one of the following:

[0283] 1) Transmission information corresponding to a specific terminal, which can include at least one of the following:

[0284] One or a group of spatial information corresponding to full-duplex transmission between the specific terminal and a target cell or network node;

[0285] Transmission mode corresponding to transmission between the specific terminal and the target cell or network node, including half-duplex or full-duplex;

[0286] Probability of successful or failed downlink reception corresponding to full-duplex transmission between the specific terminal and the target cell or network node;

[0287] One or a group of first resources corresponding to full-duplex transmission between the specific terminal and the target cell or network node, the first resources being uplink transmission resources;

[0288] One or a group of second resources corresponding to full-duplex transmission between the specific terminal and the target cell or network node, the second resources being downlink transmission resources;

[0289] One or a group of guard band resources corresponding to full-duplex transmission between the specific terminal and the target cell or network node;

[0290] One or a group of uplink transmission uplink transmission power related parameters corresponding to full-duplex transmission between the specific terminal and the target cell or network node.

[0291] 2) Transmission information corresponding to a group of terminals, which may include at least one of the following, for example:

[0292] One or a group of spatial information corresponding to terminals of a specific beam or TRP for full-duplex transmission;

[0293] Transmission mode corresponding to terminals of a specific beam or TRP for transmission, including half-duplex or full-duplex;

[0294] The probability of successful or failed downlink reception corresponding to terminals of a specific beam or TRP for full-duplex transmission;

[0295] One or a group of first resources corresponding to terminals of a specific beam or TRP for full-duplex transmission, the first resource being an uplink transmission resource;

[0296] One or a group of second resources corresponding to terminals of a specific beam or TRP for full-duplex transmission, the second resource being a downlink transmission resource;

[0297] One or a group of guard band resources corresponding to terminals of a specific beam or TRP for full-duplex transmission;

[0298] One or a group of uplink transmission uplink transmission power related parameters corresponding to terminals of a specific beam or TRP for full-duplex transmission.

[0299] 3) Transmission information corresponding to a specific area, which may include at least one of the following, for example:

[0300] One or a group of spatial information corresponding to terminals in a specific area for full-duplex transmission;

[0301] Transmission mode corresponding to terminals in a specific area for transmission, including half-duplex or full-duplex;

[0302] The probability of successful or failed downlink reception corresponding to terminals in a specific area for full-duplex transmission;

[0303] One or a group of first resources corresponding to terminals in a specific area for full-duplex transmission, the first resource being an uplink transmission resource;

[0304] One or a group of second resources corresponding to terminals in a specific area for full-duplex transmission, the second resource being a downlink transmission resource;

[0305] One or a group of guard band resources corresponding to terminals in a specific area for full-duplex transmission;

[0306] One or a group of uplink transmission uplink transmission power related parameters corresponding to terminals in a specific area for full-duplex transmission.

[0307] The specific area can include a cell, a cell group, a time advance group (TAG), a tracking area, or a radio access network notification area (RNA), etc.

[0308] In some optional embodiments, the specific area can include an area corresponding to at least one of a source cell, a target cell, a currently camped cell, a currently accessed cell, a Pcell, and an Scell, etc.

[0309] 4) Transmission information of a specific beam direction or a specific TRP or a specific SSB can include at least one of the following:

[0310] A transmission mode corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB, including half duplex or full duplex;

[0311] A probability of successful or failed downlink reception corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB;

[0312] One or a group of first resources corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB, the first resources being uplink transmission resources;

[0313] One or a group of second resources corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB, the second resources being downlink transmission resources;

[0314] One or a group of guard band resources corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB;

[0315] One or a group of uplink transmission uplink transmission power related parameters corresponding to full-duplex transmission of the terminal in the specific beam direction or the specific TRP or the specific SSB.

[0316] 5) Transmission information of a specific reference point, which can include at least one of the following, for example:

[0317] One or a group of spatial domain information corresponding to full-duplex transmission of the terminal in the specific reference point;

[0318] A transmission mode corresponding to transmission of the terminal in the specific reference point, including half duplex or full duplex;

[0319] A probability of successful or failed downlink reception corresponding to full-duplex transmission of the terminal in the specific reference point;

[0320] One or a group of first resources corresponding to full-duplex transmission of the terminal in the specific reference point, the first resources being uplink transmission resources;

[0321] one or a set of second resources corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the second resources being resources for downlink transmission;

[0322] one or a set of guard band resources corresponding to full-duplex transmission by the terminal with respect to the specific reference point;

[0323] one or a set of parameters related to uplink transmission power of uplink transmission corresponding to full-duplex transmission by the terminal with respect to the specific reference point.

[0324] It should be noted that the transmission information with respect to the specific reference point is used to inform the UE in the cell;

[0325] 6) Transmission information corresponding to a specific pathloss range or a specific RSRP range, which may, for example, include at least one of the following:

[0326] one or a set of spatial domain information corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0327] a transmission mode corresponding to transmission by the terminal with respect to the specific reference point, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range, the transmission mode including half-duplex or full-duplex;

[0328] a probability of successful or failed downlink reception corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0329] one or a set of first resources corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the first resources being resources for uplink transmission, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0330] one or a set of second resources corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the second resources being resources for downlink transmission, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0331] one or a set of guard band resources corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0332] one or a set of parameters related to uplink transmission power of uplink transmission corresponding to full-duplex transmission by the terminal with respect to the specific reference point, the pathloss or RSRP value of the terminal being within the specific pathloss range or the specific RSRP range;

[0333] In some optional embodiments, the pathloss or RSRP refers to the pathloss or RSRP between the terminal and a base station, which can be the base station of the first cell.

[0334] 7) Transmission mode, exemplarily, can include at least one of the following:

[0335] Transmission mode under specific time domain resource;

[0336] Transmission mode under specific frequency domain resource;

[0337] Transmission mode under specific TCI or beam;

[0338] Transmission mode under specific uplink transmit power;

[0339] Transmission mode under specific cell signal strength (e.g., specific RSRP);

[0340] Transmission mode under specific interference signal strength (e.g., specific Received Signal Strength Indication (RSSI)).

[0341] 8) Uplink transmit power, exemplarily, can include at least one of the following:

[0342] Uplink transmit power for full-duplex transmission under specific time domain resource;

[0343] Uplink transmit power for full-duplex transmission under specific frequency domain resource;

[0344] Uplink transmit power for full-duplex transmission under specific TCI or beam;

[0345] Uplink transmit power for full-duplex transmission under specific cell signal strength;

[0346] Uplink transmit power for full-duplex transmission under specific interference signal strength;

[0347] Uplink transmit power for full-duplex transmission under specific guard band resource.

[0348] 9) Related performance of full-duplex transmission, exemplarily, can include at least one of the following:

[0349] i) Probability of successful reception or reception error or failure, can include at least one of the following:

[0350] Probability of successful reception or failure of downlink signal for full-duplex transmission under specific time domain resource;

[0351] Probability of successful reception or failure of downlink signal for full-duplex transmission under specific frequency domain resource;

[0352] a probability of success or failure of the downlink signal of full duplex transmission under a certain TCI or beam;

[0353] a probability of success or failure of the downlink signal of full duplex transmission under a certain uplink transmit power;

[0354] a probability of success or failure of the downlink signal of full duplex transmission under a certain cell signal strength;

[0355] a probability of success or failure of the downlink signal of full duplex transmission under a certain interference signal strength;

[0356] a probability of success or failure of the downlink signal of full duplex transmission under a certain guard band resource.

[0357] wherein the success of reception can also be expressed as success of decoding, success of deciphering, or success of detection, etc.

[0358] the error or failure of reception can also be expressed as failure of decoding, error of decoding, failure of deciphering, error of deciphering, or error of detection, etc.

[0359] ii) the number of errors / failures of reception, which can include at least one of the following:

[0360] the number of failures of reception of the downlink signal of full duplex transmission under a certain frequency domain resource;

[0361] the number of failures of reception of the downlink signal of full duplex transmission under a certain TCI or beam;

[0362] the number of failures of reception of the downlink signal of full duplex transmission under a certain uplink transmit power;

[0363] the number of failures of reception of the downlink signal of full duplex transmission under a certain cell signal strength;

[0364] the number of failures of reception of the downlink signal of full duplex transmission under a certain interference signal strength;

[0365] the number of failures of reception of the downlink signal of full duplex transmission under a certain guard band resource.

[0366] 10) the resource of the guard band, which can include at least one of the following, for example:

[0367] the resource of the guard band of full duplex transmission under a certain time domain resource;

[0368] the resource of the guard band of full duplex transmission under a certain frequency domain resource;

[0369] the resource of the guard band of full duplex transmission under a certain TCI or beam;

[0370] Guard band resource for full duplex transmission under a certain uplink transmit power

[0371] Guard band resource for full duplex transmission under a certain cell signal strength

[0372] Guard band resource for full duplex transmission under a certain interference signal strength

[0373] 11) One or a set of interference information, which may include at least one of the following:

[0374] Interference information for full duplex transmission under a certain time domain resource

[0375] Interference information for full duplex transmission under a certain frequency domain resource

[0376] Interference information source for full duplex transmission under a certain TCI or beam

[0377] Interference information for full duplex transmission under a certain uplink transmit power

[0378] Interference information for full duplex transmission under a certain cell signal strength

[0379] Interference information for full duplex transmission under a certain guard band

[0380] It should be further noted that the first information may include information required for transmission (e.g., full duplex transmission), or may include full duplex transmission performance related information; or may include transmission information inferred at different granularities (e.g., different beams, different RSRP, etc.). The embodiment infers transmission information according to the AI model to perform transmission (e.g., full duplex transmission), which is beneficial to improve transmission performance, reduce overhead, and reduce latency.

[0381] Optionally, the input information of the AI model includes at least one of the following:

[0382] Signal information, distance information, path loss information, second performance information, maximum transmit power of uplink transmission, area information, frequency domain information, beam information, time delay information, service related information, state information of the terminal, state information of the network side device, state information of the satellite, perception information, non-terrestrial network (NTN) base station information, channel information, and time information; wherein the second performance information is performance information related to transmission in the full duplex transmission mode.

[0383] It should be noted that one of the terminal and the network side device is the first device, and the other is the corresponding device for transmission of the first device.

[0384] Optionally, the signal information comprises at least one of: signal strength information, signal quality information, and interference signal strength information.

[0385] Exemplarily, the signal strength information can comprise at least one of: RSRP, Reference Signal Received Quality (RSRQ), RSSI, and the like. The signal quality information can comprise at least one of: Signal Noise Ratio (SNR), Signal to Interference Plus Noise Ratio (SINR), and latency, and the like. The interference signal strength information can comprise at least one of: RSRP, RSSI, and the like. Wherein, the interference can comprise at least one of: self-interference, mutual interference, inter-cell interference, and intra-cell interference, and the like.

[0386] Optionally, the signal strength information comprises at least one of:

[0387] received strength information of an uplink signal between the first device and the second device;

[0388] received strength information of a downlink signal between the first device and the second device;

[0389] or,

[0390] the signal quality information comprises at least one of:

[0391] signal quality information of an uplink signal between the first device and the second device;

[0392] signal quality information of a downlink signal between the first device and the second device;

[0393] or,

[0394] the interference signal strength information comprises at least one of:

[0395] self-interference strength information of the first device;

[0396] mutual interference strength information of the first device;

[0397] self-interference strength information of the second device;

[0398] mutual interference strength information of the second device.

[0399] Exemplarily, one of the first device and the second device is a terminal, and the other is a network-side device, for example, a network node of a first cell, wherein the first cell is a source cell of the terminal, a target cell of the terminal, a current camping cell of the terminal, a current access cell of the terminal, a PCell of the terminal, or a SCell of the terminal.

[0400] The uplink signal between the first device and the second device can include, but is not limited to, at least one of an uplink sounding signal, an uplink reference signal, an uplink synchronization signal, and the like, for example, an SRS. The reception strength information and the signal quality information of the uplink signal between the first device and the second device can be measured by the network-side device. Exemplarily, if the reception strength information and the signal quality information of the uplink signal between the first device and the second device are used for AI inference by the terminal, the network-side device can measure the reception strength information and the signal quality information of the uplink signal between the first device and the second device and send them to the terminal.

[0401] The downlink signal between the first device and the second device can include, but is not limited to, at least one of a downlink broadcast signal, a downlink synchronization signal, a downlink reference signal, and the like, for example, an SSB, a CSI-RS, a TRS, and the like. The reception strength information and the signal quality information of the downlink signal between the first device and the second device can be measured by the terminal. Exemplarily, if the reception strength information and the signal quality information of the downlink signal between the first device and the second device are used for AI inference by the network-side device, the terminal can measure the reception strength information and the signal quality information of the downlink signal between the first device and the second device and report them to the network-side device.

[0402] The mutual interference strength information of the first device can include at least one of the mutual interference strength information of the uplink signal or the downlink signal between the first device and the second device, and the mutual interference strength information of the uplink or downlink signal between the first device and a third device; wherein the third device is of the same type as the first device, for example, the third device and the first device are both terminals in the first cell, or the third device and the first device are both network-side devices, for example, the first device is a network node of a source cell, and the third device is a network node of a target cell or a PCell and a SCell.

[0403] The mutual interference strength information of the second device can include at least one of the mutual interference strength information of the uplink signal or the downlink signal between the second device and the first device, and the mutual interference strength information of the uplink or downlink signal between the second device and a fourth device; wherein the fourth device is of the same type as the second device, for example, the fourth device and the second device are both terminals in the first cell, or the fourth device and the second device are both network-side devices, for example, the second device is a network node of a source cell, and the fourth device is a network node of a target cell or a PCell and a SCell.

[0404] Optionally, the distance information includes at least one of the following:

[0405] The distance between the first terminal and the network node of the first cell;

[0406] The distance between network nodes in the source cell and network nodes in the target cell;

[0407] The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell;

[0408] The distance between the first terminal and the second terminal;

[0409] or,

[0410] Path loss information includes at least one of the following:

[0411] Path loss between the first terminal and the network node of the first cell;

[0412] Path loss between network nodes in the source cell and network nodes in the target cell;

[0413] Path loss between network nodes of Pcell and network nodes of Scell;

[0414] The first cell includes at least one of the following: source cell, target cell, currently camped cell or currently accessed cell, Pcell, Scell; the first terminal and the second terminal are both terminals of the first cell.

[0415] For example, one of the first device and the second device is a first terminal, and the other is a network node of the first cell. Both the first terminal and the second terminal are terminals of the first cell.

[0416] For the maximum transmit power of uplink transmission, for example, it can include at least one maximum transmit power for the terminal to perform full-duplex transmission. It should be noted that the maximum transmit power of uplink transmission can be the maximum transmit power based on power control, or the maximum transmit power allowed by the RF device, or the maximum transmit power that does not cause RF or baseband signal blockage under full-duplex transmission, etc. Furthermore, the maximum transmit power of uplink transmission can include the maximum transmit power at different granularities, such as the maximum transmit power at the cell or cell group, frequency layer, TA area, TRP, network node, carrier, band, subband, or BWP granularity.

[0417] Optionally, the second performance information includes at least one of the following:

[0418] a number of times of receiving a downlink signal of full-duplex transmission under a certain time domain resource;

[0419] a number of times of receiving a downlink signal of full-duplex transmission under a certain frequency domain resource;

[0420] a number of times of receiving a downlink signal of full-duplex transmission under a certain spatial domain information;

[0421] a number of times of receiving a downlink signal of full-duplex transmission under a certain uplink transmit power;

[0422] a number of times of receiving a downlink signal of full-duplex transmission under a certain cell signal strength;

[0423] a number of times of receiving a downlink signal of full-duplex transmission under a certain interference signal strength;

[0424] a number of times of receiving a downlink signal of full-duplex transmission under a certain guard band resource.

[0425] Exemplarily, the full-duplex transmission can include full-duplex transmission between the terminal and a network node of the first cell. The certain spatial domain information can include, but is not limited to, at least one of a certain TCI and a certain beam. The certain cell signal strength can include, but is not limited to, a certain RSRP. The certain interference signal strength can include, but is not limited to, a certain RSSI.

[0426] Optionally, the area information includes at least one of: a transmission reception point, TRP, identity, a TRP group identity, a cell identity, a cell group identity, a Time Advance Group, TAG, identity, a tracking area, TA, identity, and a Radio Access Network Notification Area, RNA, identity.

[0427] Exemplarily, the TRP identity can include at least one of an identity of a source TRP, a target TRP, a current camping TRP, a current access TRP, a primary TRP, and a secondary TRP.

[0428] Exemplarily, the TRP group identity can include a group identity of at least one of a source TRP, a target TRP, a current camping TRP, a current access TRP, a primary TRP, and a secondary TRP.

[0429] Exemplarily, the cell identity can include an identity of at least one of a source cell, a target cell, a current camping cell, a current access cell, a Pcell, and a Scell.

[0430] Exemplarily, the cell identity group can include at least one of a group identity of a cell group where the source cell is located, a cell group where the target cell is located, a cell group where the current camped cell is located, a cell group where the current accessed cell is located, a cell group where the Pcell is located, and a cell group where the Scell is located, and the like.

[0431] Exemplarily, the TAG identity can include at least one of a group identity of a TAG where the source cell is located, a TAG where the target cell is located, a TAG where the current camped cell is located, a TAG where the current accessed cell is located, a TAG where the Pcell is located, and a TAG where the Scell is located, and the like.

[0432] Exemplarily, the TA identity can include at least one of an identity of a TA where the source cell is located, a TA where the target cell is located, a TA where the current camped cell is located, a TA where the current accessed cell is located, a TA where the Pcell is located, and a TA where the Scell is located, and the like.

[0433] Exemplarily, the RNA identity can include at least one of an identity of an RNA where the source cell is located, an RNA where the target cell is located, an RNA where the current camped cell is located, an RNA where the current accessed cell is located, an RNA where the Pcell is located, and an RNA where the Scell is located, and the like.

[0434] For frequency domain information, exemplarily, a frequency band, a frequency band, a frequency point, a carrier frequency, a frequency layer, or a BWP, and the like can be included. For example, the frequency domain information can include a frequency band, a frequency band, a frequency point, a carrier frequency, a frequency layer, or a BWP, and the like where at least one of the source cell, the target cell, the current camped cell, the current accessed cell, the Pcell, and the Scell, and the like actually works.

[0435] For beam information, exemplarily, one or a group of reference signal indexes or beam indexes or beam directions, and the like can be included. For example, the beam information can include a reference signal index or a beam index or a beam direction, and the like actually transmitted between the terminal and the network node of the first cell.

[0436] For time delay information, exemplarily, at least one of a propagation time delay and a Round-Trip Time (RTT), and the like can be included. For example, the transmission time delay can include a signal propagation time delay of uplink or downlink, or a signal propagation time delay between network nodes. The Round-Trip Time can include a Round-Trip Time between the terminal and the network node of the first cell.

[0437] Optionally, the service related information includes at least one of the following:

[0438] a load condition of at least one cell of the first cell;

[0439] an interference situation of at least one cell of the first cell;

[0440] a load situation corresponding to at least one spatial feature of the first cell;

[0441] an interference situation corresponding to at least one spatial feature of the first cell;

[0442] a load situation corresponding to at least one carrier or frequency point of the first cell;

[0443] an interference situation corresponding to at least one carrier or frequency point of the first cell;

[0444] The first cell includes at least one of the following: a source cell, a target cell, a current camped cell or a current accessed cell, a Pcell, a Scell; the spatial feature includes at least one of the following: an SSB, a TCI, a TRP, a beam.

[0445] It can be understood that, in the case of the first device being a terminal, the first cell is a cell of the first device; in the case of the first device being a network side device, the first device is a network node of the first cell.

[0446] Exemplarily, the load situation can include, but is not limited to, at least one of the following: uplink or downlink traffic volume, number of users, maximum uplink or downlink traffic volume, maximum number of users, etc. The interference situation can include, but is not limited to, at least one of the following: self-interference measurement value, mutual interference measurement value, maximum or minimum mutual interference link information, beam information of the maximum or minimum mutual interference link, maximum or minimum N3 mutual interference link information, beam information of the maximum or minimum N3 mutual interference link, etc., N3 being a positive integer.

[0447] Optionally, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, operator information supported by the terminal, network type information supported by the terminal, panel orientation information of the terminal, type of the terminal, network scene information of the terminal, environment information in which the terminal is located;

[0448] Or,

[0449] The state information of the network side device includes at least one of the following: transmission power information of the network side device, position information of the network side device, panel orientation information of the network side device, energy consumption status of the network side device, power status of the network side device, environment information in which the network side device is located;

[0450] Or,

[0451] The state information of the satellite includes at least one of the following: panel orientation information of the satellite, moving speed of the satellite, moving direction of the satellite.

[0452] The location information of the terminal can be a geographical position coordinate of the terminal, e.g., a Global Positioning System (GPS) coordinate, or a location range information of the terminal, e.g., a street where the terminal belongs, or a location information of the terminal relative to a camping cell or an access cell or a certain TRP or a certain group of TRPs, e.g., a direction of due east of the camping cell.

[0453] The distribution information of the terminal can include a quantity information of the terminal within different areas, e.g., a camping cell or an access cell or a certain TRP or a certain group of TRPs.

[0454] The moving direction of the terminal can be an absolute direction, e.g., 40 degrees east of south, or a relative direction, e.g., a direction relative to a certain base station or a reference point.

[0455] The type of the terminal, e.g., a power class.

[0456] The network scenario information of the terminal, e.g., an indoor hotspot (inH), an Urban Macro (UMa) cell or a Rural Macro (RMa) cell, etc., or a homogeneous / heterogeneous network, i.e., with or without overlapping coverage.

[0457] The environment information where the terminal is located, e.g., weather information.

[0458] The transmission power information of the network-side device, e.g., an actual transmission power of a network node of the first cell.

[0459] The location information of the network-side device, e.g., a geographical position information of a network node of the first cell.

[0460] The environment information where the network-side device is located, e.g., weather information.

[0461] The perception information can be understood as information obtained through perception. Exemplarily, the perception information can include but is not limited to communication environment information, scenario information, channel state information (e.g., Line Of Sight (LOS) path, NON Line Of Sight (NLOS) or blocking, etc.), a number of terminals, etc. For example, at least one of whether there is an obstacle under a certain beam and a number of obstacles, or a number of terminals or devices under coverage of a certain beam, etc.

[0462] The NTN base station information may exemplarily include at least one of ephemeris information, a reference position or a moving track of a cell in the NTN scenario, and the like. For example, for a low-earth orbit (LEO) scenario, as the satellite moves, the cell on the earth is moving, and thus the moving track of the cell can be obtained in this scenario; or for a geostationary orbit (GEO) scenario, as the satellite moves, the cell on the earth is fixed, and it can be considered that there is a reference position, and thus the reference position of the cell can be obtained in this scenario.

[0463] The channel information may exemplarily include multipath information of a channel, for example, first path or strongest path information of a terminal and different base stations or TRPs.

[0464] The time information may exemplarily be an accurate time, for example, 13:25:38; or may also be a time range, for example, 13:00-14:00, morning / afternoon, day / night, and the like; or may be timing information obtained through a first RAT, and the first RAT may be a different RAT from the RAT adopted for the first transmission, for example, the first RAT may be Bluetooth, Wi-Fi, 3G, 4G or 5G, and the like.

[0465] It should be noted that the input information is beneficial to improve the accuracy and flexibility of AI model inference, and thus the performance of the AI model.

[0466] In some optional embodiments, the execution subject of the AI model inference includes at least one of the following:

[0467] 1) a terminal;

[0468] Since the information mastered by the terminal is the most timely, the execution of the AI model inference by the terminal-side device can ensure that the inference is performed according to the latest information, and thus is beneficial to improve the reliability of the inference result.

[0469] 2) a network-side device;

[0470] Exemplarily, the network-side device includes at least one of a base station, a TRP, a core network device (such as a core network device specially used for model training).

[0471] The base station or the TRP may be a base station or a TRP currently camped by the terminal, currently accessed by the terminal, or targeted for handover or reselection by the terminal. The execution of the AI model inference by the network-side device can reduce the complexity and cost of the terminal, and the power consumption overhead.

[0472] 3) a server;

[0473] The server can be a device specially used for training or inference or providing AI-related information, or can be a third-party server, or can be a device provided by an OTT service provider, a third-party service provider, or the Internet, etc. AI model inference through a dedicated server can improve the performance of AI while reducing the complexity and cost of network devices and terminal devices.

[0474] In some optional embodiments, when the terminal performs model inference, the method can further include: the terminal obtaining an AI model from other terminals / network side devices / servers, and obtaining first information based on input information using the AI model. At least part of the input information for AI model inference can be sent by the network side device to the terminal, and the signal or channel for sending at least part of the input information includes at least one of the following: a media access control control element (MAC CE), a radio resource control (RRC) message, a non-access stratum (NAS) message, user plane data, downlink control information (DCI) information, a system information block (SIB), a PDCCH, a PDSCH, MSG2 information, MSG4 information, and MSGB information.

[0475] In some optional embodiments, when the network side device performs AI model inference, the method can further include: the network side device obtaining an AI model from a terminal / other network side devices / servers, and obtaining first information based on input information using the AI model. At least part of the input information for AI model inference is reported by the terminal, and the signal or channel for reporting at least part of the input information includes at least one of the following: a MAC CE, an RRC message, a NAS message, user plane data, MSG1 information, MSGA information, MSG3 information, a PUCCH, a PUSCH, a PRACH, and an SRS.

[0476] In some optional embodiments, when the server performs AI model inference, at least part of the input information for AI model inference is indicated by the terminal or the network side device, for example, through an OTT message.

[0477] Optionally, the method further includes:

[0478] The first device obtains first configuration information;

[0479] The first configuration information includes at least one of the following:

[0480] An AI model or an AI model identifier;

[0481] application scope of the AI model inference;

[0482] cycle of the AI model inference;

[0483] validity duration of the AI model inference;

[0484] trigger condition of the AI model inference;

[0485] configuration parameter of the AI model, the configuration parameter of the AI model comprising at least one of: input information of the AI model, output information of the AI model, type of the input information of the AI model, type of the output information of the AI model;

[0486] first indication information, used for indicating whether joint inference is supported or is needed.

[0487] application scope of the AI model inference, for example, frequency range to which the AI model inference can be applied, or cell or cell list to which the AI model inference can be applied, or interval in which the location of the terminal is located, or range in which the distance between the terminal and the base station is located.

[0488] The validity duration can comprise a start time and an end time of the inference, or can be a specific time length, for example, 1 hour, 2 hours, etc.

[0489] The trigger condition of the AI model inference is used to trigger the AI model inference, and it needs to be noted that the trigger condition is not the only condition for triggering or activating the AI model inference, and the AI model inference can also be triggered or activated in combination with other information.

[0490] Joint inference refers to that at least part of the input information of the AI model is provided by other devices when the first device uses the AI model for inference. For example, when the terminal uses the AI model for inference, at least part of the input information of the AI model is sent by the network side setting; when the network side device uses the AI model for inference, at least part of the input information of the AI model is reported by the terminal; when the server uses the AI model for inference, at least part of the input information of the AI model is sent by the terminal and / or the network side device.

[0491] Exemplarily, the first device can obtain the first configuration information from the second device, and can perform AI model inference according to the first configuration information, which is beneficial to more accurate AI inference control.

[0492] Optionally, the method further comprises:

[0493] The first device obtains second indication information, the second indication information being used to indicate activation information or deactivation information of the AI model.

[0494] The first device activates or deactivates the AI model according to the second indication information.

[0495] For example, in a case where the second indication information indicates the activation information of the AI model, the first device can activate the AI model based on the second indication information; in a case where the second indication information indicates the deactivation information of the AI model, the first device can deactivate the AI model based on the second indication information.

[0496] In this embodiment, the AI model is activated or deactivated based on the second indication information, which is beneficial to improve the flexibility of activation or deactivation of the AI model.

[0497] Optionally, the trigger condition for using the AI model to perform inference includes at least one of the following:

[0498] a timer timeout for triggering AI inference;

[0499] selection of transmission based on full-duplex transmission configuration;

[0500] a failure probability corresponding to full-duplex transmission is greater than or equal to a first threshold;

[0501] an uplink transmission power corresponding to full-duplex transmission is greater than or equal to a second threshold, or the uplink transmission power corresponding to full-duplex transmission reaches a maximum transmission power;

[0502] an interference signal strength corresponding to full-duplex transmission is greater than or equal to a third threshold;

[0503] the terminal performs cell or TRP reselection;

[0504] the terminal performs cell or TRP switching;

[0505] service arrival;

[0506] receiving indication information used to indicate to perform AI inference;

[0507] a change in the location of the terminal or a change in the movement parameter of the terminal;

[0508] a change in the spatial domain information of the terminal or a change in the transmission filter.

[0509] In this embodiment, at least one of the first threshold, the second threshold, and the third threshold can be predefined by a protocol or can be configured by a network side device, etc.

[0510] The timer for triggering AI inference can be a newly defined specific timer for triggering AI inference, and the AI model inference is triggered when the first device detects that the specific timer is overdue. It can be understood that the timer for triggering AI inference can also reuse an existing timer.

[0511] For selecting transmission based on full-duplex transmission configuration, for example, the network side device configures a special full-duplex transmission configuration, if the transmission based on the full-duplex transmission configuration is selected, the AI model is triggered for inference. Wherein, the full-duplex transmission configuration can also be referred to as full-duplex transmission parameter.

[0512] For triggering AI model inference when terminal performs cell or TRP switching, specifically, the AI model inference can be triggered when the cell switching condition is met, exemplarily, the cell switching condition can include at least one of the following: the measurement result (L1 or L3 RSRP, RSRQ or RSSI, etc.) of the source cell is greater than or less than a first target threshold, the measurement result of the target cell or neighboring cell is better than the source cell, the measurement result of the target cell or neighboring cell is greater than a second target threshold, the measurement result of the source cell is less than a specified threshold and the measurement result of the target cell or neighboring cell is greater than a third target threshold, the load of the source cell is greater than a fourth target threshold.

[0513] The failure probability of full-duplex transmission is greater than or equal to a first threshold, exemplarily, which can include at least one of the following:

[0514] The number of downlink signal reception failures of full-duplex transmission under one or a group of time domain resources is greater than or equal to a first threshold 1;

[0515] The number of downlink signal reception failures of full-duplex transmission under one or a group of frequency domain resources is greater than or equal to a first threshold 2;

[0516] The number of downlink signal reception failures of full-duplex transmission under one or a group of TCI or beams is greater than or equal to a first threshold 3;

[0517] The number of downlink signal reception failures of full-duplex transmission under one or a group of uplink transmission power is greater than or equal to a first threshold 4;

[0518] The number of downlink signal reception failures of full-duplex transmission under one or a group of cell signal strengths is greater than or equal to a first threshold 5;

[0519] The number of downlink signal reception failures of full-duplex transmission under one or a group of interference signal strengths is greater than or equal to a first threshold 6;

[0520] The number of downlink signal reception failures of full-duplex transmission under one or a group of guard band resources is greater than or equal to a first threshold 7;

[0521] The number of failures of switching different transmission modes is greater than or equal to a first threshold 8.

[0522] The first threshold 1 to the first threshold 8 can be at least partially the same or can be at least partially different.

[0523] The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to a second threshold. Exemplarily, the second threshold can include at least one of the following:

[0524] The uplink transmission power of the full-duplex transmission under one or a group of time domain resources is greater than or equal to a second threshold 1;

[0525] The uplink transmission power of the full-duplex transmission under one or a group of frequency domain resources is greater than or equal to a second threshold 2;

[0526] The uplink transmission power of the full-duplex transmission under one or a group of TCI or beams is greater than or equal to a second threshold 3;

[0527] The uplink transmission power of the full-duplex transmission under one or a group of cell signal strengths is greater than or equal to a second threshold 4;

[0528] The uplink transmission power of the full-duplex transmission under one or a group of interference signal strengths is greater than or equal to a second threshold 5;

[0529] The uplink transmission power of the full-duplex transmission under one or a group of guard band resources is greater than or equal to a second threshold 6;

[0530] The difference between the transmission power corresponding to the full-duplex transmission and the maximum transmission power is greater than or equal to a second threshold 7.

[0531] The second threshold 1 to the second threshold 7 can be at least partially the same or can be at least partially different.

[0532] The uplink transmission power corresponding to the full-duplex transmission reaches the maximum transmission power. Exemplarily, the maximum transmission power can include at least one of the following:

[0533] The uplink transmission power of the full-duplex transmission under one or a group of time domain resources reaches the corresponding maximum transmission power;

[0534] The uplink transmission power of the full-duplex transmission under one or a group of frequency domain resources reaches the corresponding maximum transmission power;

[0535] The uplink transmission power of the full-duplex transmission under one or a group of TCI or beams reaches the corresponding maximum transmission power;

[0536] The uplink transmission power of the full-duplex transmission under one or a group of cell signal strengths reaches the corresponding maximum transmission power;

[0537] The uplink transmission power of the full-duplex transmission under one or a group of interference signal strengths reaches a corresponding maximum transmission power;

[0538] The uplink transmission power of the full-duplex transmission under one or a group of guard band resources reaches a corresponding maximum transmission power.

[0539] The interference signal strength of the full-duplex transmission under one or a group of time domain resources is greater than or equal to a third threshold 1;

[0540] The interference signal strength of the full-duplex transmission under one or a group of time domain resources is greater than or equal to a third threshold 1;

[0541] The interference signal strength of the full-duplex transmission under one or a group of frequency domain resources is greater than or equal to a third threshold 2;

[0542] The interference signal strength of the full-duplex transmission under one or a group of TCI or beams fails to be received for a number of times greater than or equal to a third threshold 3;

[0543] The interference signal strength of the full-duplex transmission under one or a group of uplink transmission powers is greater than or equal to a third threshold 4;

[0544] The interference signal strength of the full-duplex transmission under one or a group of cell signal strengths RSRP is greater than or equal to a third threshold 5;

[0545] The interference signal strength of the full-duplex transmission under one or a group of guard band resources is greater than or equal to a third threshold 6.

[0546] The third threshold 1 to the third threshold 6 can be at least partially the same or can be at least partially different.

[0547] The arrival of the service can include the arrival of UL service or data or the arrival of DL service or data. In some optional embodiments, it can be a specific type of service arrival, for example, a service with high latency requirement, or a service with high reliability requirement, etc.

[0548] The indication information for indicating to perform AI inference can be, for example, indication information for indicating to obtain first information based on an AI model.

[0549] The position of the terminal changes, for example, the terminal moves to a specific position, such as the edge of a cell; or the amount of change of the position of the terminal exceeds a corresponding threshold. The movement parameter of the terminal can include at least one of the speed, direction, and acceleration of the terminal. The movement parameter of the terminal changes, for example, the speed or acceleration of the terminal exceeds a corresponding threshold.

[0550] The spatial domain information of the terminal can include information such as a beam. The AI inference is triggered when the spatial domain information of the terminal changes, for example, when beam failure recovery is performed.

[0551] It should be noted that the trigger condition for using the AI model for inference can mean that the AI inference will be triggered as long as at least one of the trigger conditions is met; or it can also mean that the AI inference can be performed when at least one of the trigger conditions is met, but whether the AI inference is triggered or not needs to be further considered in combination with the AI-related capabilities, the application range of the AI model inference, and other indication information of the network side, etc.

[0552] For example, when at least one of the trigger conditions is met, the AI model-based inference is immediately triggered; or when at least one of the trigger conditions is met, it is indicated that the AI model-based inference can be enabled, but whether to trigger or not needs to be determined in combination with the AI-related capabilities, the application range of the AI model inference, and other indication information of the network side, etc.

[0553] Optionally, the method further includes:

[0554] The first device performs a first operation, and the first operation includes at least one of the following:

[0555] The second information includes at least one of the following: the first information, at least part of the input information of the AI model, and the state information of the first device;

[0556] Falling back to determining the first information in a non-AI manner;

[0557] Triggering adjustment of the AI model;

[0558] Triggering training of the AI model;

[0559] Triggering supervision of the AI model.

[0560] The non-AI manner can also be referred to as a legacy manner, which means determining to suspend or give up obtaining the first information based on the AI model. In this scenario, the result of this AI model inference does not meet the expectations, and the result can be given up. It can be understood that the non-AI manner is relative to determining the first information based on the AI model.

[0561] The adjustment of the AI model can include at least one of the following: updating of the model, changing of the model, switching of the model, Fine tuning of the model, changing of the model input information, and changing of the model output information, etc.

[0562] Optionally, the trigger condition of the first operation includes at least one of the following:

[0563] the first information satisfying the performance requirement is not obtained after the AI model inference exceeds M time length;

[0564] the AI inference using the AI model is not successfully completed, or the AI inference using the AI model is successfully completed;

[0565] N times of AI inference using the AI model are performed;

[0566] wherein M and N are positive integers, which can be preset values.

[0567] In this embodiment, at least one of N and N can be predefined by a protocol, or can be configured by a network side device.

[0568] For the first information satisfying the performance requirement not being obtained after the AI model inference exceeds M time length, for example, a number of failures of full-duplex transmission based on the first information is greater than or equal to a preset number.

[0569] the AI inference using the AI model is not successfully completed, for example, the AI inference using the AI model fails or the first information is not successfully obtained using the AI model, and the like.

[0570] the AI inference using the AI model is successfully completed, for example, the first information is successfully obtained using the AI model.

[0571] This embodiment performs the first operation in the case of meeting the triggering condition, which is conducive to guaranteeing that accurate transmission information is obtained.

[0572] In some optional embodiments, the indicators of the AI model inference include at least one of the following:

[0573] complexity of the AI model;

[0574] time delay of the AI model inference;

[0575] success rate of the AI model inference;

[0576] reliability of a result output by the AI model.

[0577] The complexity of the AI model can be defined as different complexity indicator requirements of the AI model for different types / capabilities of network side devices or terminals or servers, for example, the complexity of the AI model used by a general terminal should not exceed a first value.

[0578] The time delay of the AI model inference can be understood as a time length of prediction or inference or processing using the AI model. Specifically, the time length of prediction or inference or processing using the AI model should not exceed a first preset time length.

[0579] The success rate of AI model inference can be understood as the success rate of using the AI model for prediction or inference or processing within a certain time length. For example, the success rate of AI model prediction can be the ratio of the number of successful predictions using the AI model within a certain time length to the total number of predictions within the certain time length, or the success rate of AI model prediction can be a value determined according to at least two success rates counted within at least two certain time lengths, for example, the average of at least two success rates, the success rate counted within each certain time length being the ratio of the number of successful predictions using the AI model within the certain time length to the total number of predictions within the certain time length. The certain time length can be a protocol predefined time length or a network side device configured time length.

[0580] Specifically, the success rate of using the AI model for prediction or inference or processing is not less than a second value.

[0581] The reliability of the result output by the AI model, for example, the probability that the first information inferred by the AI model meets the performance requirement is greater than or equal to a third value.

[0582] Exemplarily, the first value, the second value and the third value can be protocol predefined values or network side device configured values.

[0583] It should be noted that the index of AI model inference can be used to determine whether the performance of AI model inference meets the index requirement.

[0584] Optionally, the method further comprises:

[0585] The first device trains at least part of the AI model;

[0586] Or,

[0587] The first device receives model information, and the model information is used to determine at least part of the AI model.

[0588] In an embodiment, at least part of the AI model is trained by the first device, in which case, if AI inference is performed by the first device, the first device can perform inference based on the trained at least part of the AI model; if AI model is performed by the second device, the first device can send the trained at least part of the AI model or the identifier of the at least part of the AI model to the second device.

[0589] In some optional embodiments, the first device can obtain at least part of the input information sent by at least one device for AI model training, for example, if the first device is a terminal, the first device can receive at least part of the input information sent by at least one of the network side device, the server and the satellite, and train at least part of the AI model based on the received at least part of the input information.

[0590] In another implementation, the first device can receive model information, e.g., can receive the model information from the second device, the model information can include at least part of the AI model or an identification of at least part of the AI model, etc., and then the first device can perform inference based on at least part of the AI model.

[0591] In some optional embodiments, the first device can send at least part of the input information for AI model training to the second device, and then the second device can train at least part of the AI model based on the received at least part of the input information.

[0592] It can be understood that the parameter items included in the input information for AI model training and the parameter items included in the input information for AI model inference can all be the same or can be partially the same.

[0593] It also needs to be explained that the training of the AI model can be training performed before inference, so as to obtain the AI model; or, online training can also be performed on the AI model to update the AI model, so as to improve the accuracy and reliability of the AI model. The training of the AI model can be performed by a terminal, a base station, a TRP, a core network device or a server, which is not limited in particular. The server includes but is not limited to one of the following: an OTT server, a third-party service provider server, an Internet server, etc.

[0594] In some optional embodiments, the related information for AI model training includes at least one of the following:

[0595] The input information for AI model training includes at least each parameter item of the input information for AI model inference;

[0596] The label or true value or output information of the model for AI model training;

[0597] The loss function for AI model training;

[0598] The AI algorithm or AI algorithm index for AI model training;

[0599] The reward information or adjustment information or feedback information for AI model training.

[0600] The reward information or adjustment information or feedback information for AI model training can include at least one of the following:

[0601] Whether fallback occurs (i.e., traditional way is adopted to obtain full-duplex transmission resources);

[0602] The number of times of fallback occurs;

[0603] Difference between failure probability of AI inference full-duplex transmission and failure probability of actual full-duplex transmission

[0604] Number of failures of AI inference.

[0605] Optionally, the trigger type of AI model training includes at least one of the following: conditional or event trigger, periodic trigger, and semi-static trigger.

[0606] Optionally, the condition or event triggering AI model training includes at least one of the following:

[0607] Timer timeout for triggering AI model training;

[0608] TAG-related timer timeout;

[0609] Receiving indication information indicating AI training;

[0610] Terminal accessing a new cell;

[0611] Terminal switching frequency or frequency band;

[0612] Terminal switching operator or public land mobile network (PLMN);

[0613] AI model inference failure;

[0614] AI model continuous inference failure P times, P being a positive integer;

[0615] AI model inference failure number reaching a fourth threshold;

[0616] Using an AI model for inference;

[0617] Terminal moving to a new cell or tracking area or geographic location;

[0618] Terminal moving speed changing, or terminal moving speed change being greater than or equal to a fifth threshold;

[0619] Terminal RSRP measurement changing, or terminal RSRP measurement change being greater than or equal to a sixth threshold;

[0620] Duration of timer timeout for AI model training reaching a first duration;

[0621] K times of model supervision occurring or S consecutive times of model supervision occurring, K and S being positive integers;

[0622] Terminal external environment changing;

[0623] The moving speed of the terminal is greater than or equal to a seventh threshold, or the acceleration of the terminal is greater than or equal to an eighth threshold;

[0624] The position of the terminal changes, or the change amount of the position of the terminal is greater than or equal to a ninth threshold;

[0625] The moving parameter of the terminal changes;

[0626] The spatial domain information of the terminal changes, or the spatial domain transmission filter of the terminal changes;

[0627] The network-side device configures a full-duplex transmission configuration;

[0628] The failure probability corresponding to the full-duplex transmission is greater than or equal to a tenth threshold;

[0629] The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to an eleventh threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches the maximum transmission power;

[0630] The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold;

[0631] The terminal performs cell or TRP switching;

[0632] The terminal performs cell or TRP reselection;

[0633] The service arrives;

[0634] The indication information for indicating that the full-duplex transmission information is determined based on the AI model is received.

[0635] In the embodiment, at least one of the fourth threshold to the twelfth threshold is predefined by a protocol or indicated by the network-side device.

[0636] The indication information for indicating AI training is received, for example, the base station sends the indication information of model training to the terminal through the MAC CE command.

[0637] The change amount of the moving speed of the terminal is greater than or equal to a fifth threshold, that is, the moving speed of the terminal changes obviously or drops sharply in a short time, for example, from 250kM / h to 3km / H.

[0638] The external environment of the terminal changes, for example, the change information of the environment can be obtained through sensing.

[0639] The moving parameter of the terminal can include but is not limited to at least one of the moving speed, acceleration and moving direction of the terminal.

[0640] The spatial domain information of the terminal can include but is not limited to at least one of the selected beam, TCI and SSB of the terminal.

[0641] For the network side device configured with the full duplex transmission configuration, for example, in the case that the network side device is configured with a special full duplex transmission configuration, the AI model training is triggered; in the case that the terminal performs full duplex transmission based on the full duplex transmission configuration, the AI model performs inference.

[0642] The failure probability corresponding to the full duplex transmission is greater than or equal to a tenth threshold, which may exemplarily include at least one of the following:

[0643] The number of downlink signal reception failures of the full duplex transmission under one or a group of time domain resources is greater than or equal to a tenth threshold 1;

[0644] The number of downlink signal reception failures of the full duplex transmission under one or a group of frequency domain resources is greater than or equal to a tenth threshold 2;

[0645] The number of downlink signal reception failures of the full duplex transmission under one or a group of TCI or beams is greater than or equal to a tenth threshold 3;

[0646] The number of downlink signal reception failures of the full duplex transmission under one or a group of uplink transmission powers is greater than or equal to a tenth threshold 4;

[0647] The number of downlink signal reception failures of the full duplex transmission under one or a group of cell signal strengths is greater than or equal to a tenth threshold 5;

[0648] The number of downlink signal reception failures of the full duplex transmission under one or a group of interference signal strengths is greater than or equal to a tenth threshold 6;

[0649] The number of downlink signal reception failures of the full duplex transmission under one or a group of guard band resources is greater than or equal to a tenth threshold 7;

[0650] The number of failures of switching different transmission modes is greater than or equal to a tenth threshold 8.

[0651] Among them, the tenth threshold 1 to the tenth threshold 8 can be at least partially the same or at least partially different.

[0652] The uplink transmission power corresponding to the full duplex transmission is greater than or equal to an eleventh threshold, which may exemplarily include at least one of the following:

[0653] The uplink transmission power of the full duplex transmission under one or a group of time domain resources is greater than or equal to an eleventh threshold 1;

[0654] The uplink transmission power of the full duplex transmission under one or a group of frequency domain resources is greater than or equal to an eleventh threshold 2;

[0655] The uplink transmission power of the full duplex transmission under one or a group of TCI or beams is greater than or equal to an eleventh threshold 3;

[0656] the uplink transmit power of the full-duplex transmission under one or a set of cell signal strengths is greater than or equal to an eleventh threshold 4;

[0657] the uplink transmit power of the full-duplex transmission under one or a set of interference signal strengths is greater than or equal to an eleventh threshold 5;

[0658] the uplink transmit power of the full-duplex transmission under one or a set of guard band resources is greater than or equal to an eleventh threshold 6;

[0659] a difference between the transmit power corresponding to the full-duplex transmission and the maximum transmit power is greater than or equal to an eleventh threshold 7.

[0660] The eleventh threshold 1 to the eleventh threshold 7 can be at least partially the same or at least partially different.

[0661] The uplink transmit power corresponding to the full-duplex transmission reaches the maximum transmit power, which can exemplarily include at least one of the following:

[0662] the uplink transmit power of the full-duplex transmission under one or a set of time domain resources reaches the corresponding maximum transmit power;

[0663] the uplink transmit power of the full-duplex transmission under one or a set of frequency domain resources reaches the corresponding maximum transmit power;

[0664] the uplink transmit power of the full-duplex transmission under one or a set of TCI or beams reaches the corresponding maximum transmit power;

[0665] the uplink transmit power of the full-duplex transmission under one or a set of cell signal strengths reaches the corresponding maximum transmit power;

[0666] the uplink transmit power of the full-duplex transmission under one or a set of interference signal strengths reaches the corresponding maximum transmit power;

[0667] the uplink transmit power of the full-duplex transmission under one or a set of guard band resources reaches the corresponding maximum transmit power.

[0668] The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold, which can exemplarily include at least one of the following:

[0669] the interference signal strength of the full-duplex transmission under one or a set of time domain resources is greater than or equal to a twelfth threshold 1;

[0670] the interference signal strength of the full-duplex transmission under one or a set of frequency domain resources is greater than or equal to a twelfth threshold 2;

[0671] The number of downlink signal receiving failures of full-duplex transmission under one or a group of TCIs or beams is greater than or equal to a twelfth threshold 3;

[0672] The interference signal strength of full-duplex transmission under one or a group of uplink transmission powers is greater than or equal to a twelfth threshold 4;

[0673] The interference signal strength of full-duplex transmission under one or a group of cell signal strengths RSRP is greater than or equal to a twelfth threshold 5;

[0674] The interference signal strength of full-duplex transmission under one or a group of guard band resources is greater than or equal to a twelfth threshold 6.

[0675] Among them, the twelfth threshold 1 to the twelfth threshold 6 can be at least partially the same or at least partially different.

[0676] The service arrival can include UL service or data arrival or DL service or data arrival. In some optional embodiments, it can be a specific type of service arrival, for example, a service with high delay requirement, or a service with high reliability requirement, etc.

[0677] The position of the terminal changes, for example, the position of the terminal moves to a specific position, such as the edge of a cell; or the amount of change of the position of the terminal exceeds a corresponding threshold. The movement parameter of the terminal can include at least one of the speed, direction, acceleration, etc. of the terminal. The movement parameter of the terminal changes, for example, the speed or acceleration of the terminal exceeds a corresponding threshold.

[0678] The spatial information of the terminal can include beam information, etc. The AI model training is triggered when the spatial information of the terminal changes, for example, the AI model training is triggered when beam failure recovery is performed.

[0679] It should be noted that the triggering condition of the AI model training can mean that as long as at least one of the triggering conditions is met, the AI training will be triggered; or it can also mean that at least one of the triggering conditions is met, and the AI training can be performed, but whether to trigger the AI training still needs to be further determined in combination with considering the AI-related capabilities and other indication information of the network side, etc.

[0680] For example, when at least one of the triggering conditions is met, the training of the AI model is immediately triggered; or when at least one of the triggering conditions is met, it indicates that the AI model-based training can be enabled, but whether to trigger needs to be determined in combination with considering the AI-related capabilities and other indication information of the network side, etc.

[0681] In some optional embodiments, the AI model training is periodic, and the periodic configuration information includes at least one of the following:

[0682] a starting point of periodic model training; for example, the terminal receives the configuration information of the network and performs periodic model training;

[0683] an interval of periodic model training; for example, at least one model training is triggered every interval N time length;

[0684] a number of model training times or a model training time length in a period.

[0685] In some optional embodiments, the AI model training is semi-statically triggered, and the semi-static triggering includes at least one of the following:

[0686] triggering the issuance and activation of semi-static configuration information based on specific conditions / events; wherein the semi-static configuration information includes a starting point of model training, a period, a duration in the period, etc.

[0687] Semi-static configuration information is configured by RRC, and semi-static training of the model is activated / deactivated by DCI or MAC-CE.

[0688] Optionally, the label for AI model training includes at least one of the following:

[0689] obtaining or not obtaining first information satisfying a performance requirement;

[0690] a number of obtained first information;

[0691] a time length of AI model training;

[0692] energy consumption of AI model training;

[0693] first information required for transmission between the terminal and the network node of the first cell.

[0694] The label for AI model training can also be referred to as a true value or real value for AI model training.

[0695] The first information satisfying the performance requirement may, for example, include at least one of the following:

[0696] a success rate of full-duplex transmission based on the first information is greater than or equal to a first threshold value;

[0697] a failure rate of full-duplex transmission based on the first information is lower than a second threshold value;

[0698] a transmission power required for successful full-duplex transmission based on the first information is lower than a third threshold value;

[0699] a number of transmissions required for successful full-duplex transmission based on the first information is lower than a fourth threshold value;

[0700] The residual interference of the full-duplex transmission based on the first information is lower than a fifth threshold value.

[0701] The signal-to-noise ratio of the full-duplex transmission based on the first information is lower than a sixth threshold value.

[0702] The residual interference can be understood as the residual interference after interference cancellation or interference suppression. The signal-to-noise ratio of the full-duplex transmission can be used to represent the residual interference.

[0703] The length of the AI model training, for example, the length of the AI model training is greater than or equal to the target length, and it is considered that the training is completed.

[0704] The first information required for transmission between the terminal and the network node of the first cell, for example, if the performance information of the full-duplex transmission between the terminal and the target cell is greater than or equal to the target value, it is considered that the training is completed.

[0705] In some optional embodiments, the label for AI model training can further include at least one of the following:

[0706] At least one spatial domain information;

[0707] At least one transmission mode;

[0708] At least one first performance information;

[0709] At least one first transmission parameter;

[0710] At least one second transmission parameter;

[0711] At least one resource of the guard band;

[0712] At least one related parameter of the uplink transmit power;

[0713] At least one interference information.

[0714] It should be noted that the acquisition method of the label for AI model training can include feedback based on the terminal, or can be obtained by network side device or terminal measurement.

[0715] In some optional embodiments, the execution subject of the AI model training can include at least one of the following:

[0716] 1), the terminal;

[0717] 2), the network side device;

[0718] Exemplarily, the network side device includes at least one of the base station, the TRP, the core network device (such as the core network device specially used for model training).

[0719] Wherein, the base station or TRP can be the base station or TRP where the terminal currently resides or the terminal currently accesses or the terminal target switches or the terminal target reselects.

[0720] 3) Server;

[0721] The server can be a device specially used for training or inference or providing AI-related information, or can be a third-party server, or can be a device server provided by an OTT service provider, a third-party service provider, or the Internet, etc. The server can be a device specially used for training or inference or providing AI-related information, or can be a third-party server, or can be a device provided by an OTT service provider, a third-party service provider, or the Internet, etc.

[0722] In some optional embodiments, performing part of the model training only at the terminal side, the network side or the server side, or performing joint training at the terminal side, the network side and the server side, can include at least one of the following:

[0723] The terminal side reports at least part of the output information of the model training to the network side or the server side, and the network side or the server side takes the reported information of the terminal side (i.e. the output information of the terminal model training) as one of the input contents of its own model training;

[0724] The network side sends at least part of the output information of the model training to the terminal or the server side, and the terminal or the server side takes the information sent by the network side (i.e. the output information of the network side model training) as one of the input contents of its own model training;

[0725] The terminal side, the network side or the server side performs offline model training, and then the terminal side, the network side or the server side performs fine tuning in the actual network.

[0726] In some optional embodiments, when at least part of the training of the AI model occurs at the network side or the server side, after the training of the AI model is completed, the network side or the server side downloads at least part of the trained AI model to the terminal.

[0727] In some optional embodiments, when at least part of the training of the AI model occurs at the terminal side or the server side, there can be multiple sets of trained AI models at the terminal side or the server side, and the terminal side or the server side can report auxiliary information to the network side, and the network side determines and instructs which set of AI model to use for AI inference.

[0728] The multiple AI models can have at least one of the following differences: a difference in training data sets, a difference in label information, a difference in input information, and a difference in inference output. The auxiliary information can include an identification ID of the multiple AI models and a classification identification of the data sets.

[0729] The network side indication can be a network direct indication of at least one of the following: an ID of the AI model, an ID of the data set, and data collection related configuration information. The terminal or server can determine which AI model to use for model inference according to at least one of the received AI model ID, data set ID, and data collection related configuration information.

[0730] In some optional embodiments, the determination condition of the completion of the AI model training includes at least one of the following:

[0731] The loss function used for AI model training satisfies a first preset condition;

[0732] The number of times of training of the AI model reaches a first preset number of times;

[0733] The number of iterations of Fine tuning of the AI model reaches a second preset number of times;

[0734] At least one label used for AI model training satisfies a corresponding threshold condition.

[0735] The loss function used for AI model training satisfies a first preset condition, for example, the loss function used for AI model training satisfies a predefined requirement index or value, for example, the error of training is less than a predefined threshold, wherein the loss function can be at least one of the following: mean square error or normalized mean square error of predicted value and true value, and mean absolute error of predicted value and true value.

[0736] The number of times of model training reaches a predefined value;

[0737] The number of iterations of Fine tuning reaches a predetermined value;

[0738] At least one label used for AI model training satisfies a corresponding threshold condition, for example, at least one piece of information in the label used for AI model training is greater than or equal to a corresponding threshold, or at least one piece of information in the label used for AI model training is less than or equal to a corresponding threshold.

[0739] It can be understood that when the inference environment and the training environment are quite different, the performance of full-duplex transmission based on the first information inferred by the AI model will become very poor, that is, the inferred first information is not accurate enough. Therefore, the actual inference performance determined based on the first information of the AI model needs to be supervised, and a series of adjustment measures are triggered according to the supervision result to ensure the reliability of the AI model.

[0740] Optionally, the method further comprises:

[0741] The first device supervises the AI model;

[0742] Or,

[0743] The first device receives a model supervision result of the AI model.

[0744] Exemplarily, the model supervision result can include at least one of an error between a predicted value and a true value of the AI model, a communication system performance index, etc. Wherein, the communication system performance index can include at least one of a transmission delay, a throughput, etc.

[0745] In an embodiment, the AI model can be supervised by the first device, and then whether the AI model needs to be updated or retrained, or whether the AI model needs to be switched, etc. can be determined based on the model supervision result of the AI model.

[0746] In some optional embodiments, the first device can also send the model supervision result to the second device, so that the second device determines whether the AI model needs to be updated or retrained, etc. based on the model supervision result of the AI model.

[0747] In another embodiment, the supervision of the AI model can be performed by the second device, and the model supervision result is sent to the first device, so that the first device determines whether the AI model needs to be updated or retrained, or whether the AI model needs to be switched, etc. based on the model supervision result of the AI model.

[0748] In some optional embodiments, the label for AI model supervision can be the same as the label used for AI model training, or can be a label specially used for AI model supervision. Wherein, the label for AI model supervision can also be referred to as the true value or the real value of AI model supervision.

[0749] Optionally, the configuration information for AI model supervision includes at least one of:

[0750] An AI model or an AI model identifier that needs to be supervised;

[0751] A period of model supervision;

[0752] A duration of model supervision;

[0753] Detection window related information of model supervision;

[0754] Triggering conditions of model supervision;

[0755] Indicators of model supervision;

[0756] Labels of model supervision.

[0757] The model supervision detection window related information can include at least one of a length of the supervision window, and a number of samples for model supervision.

[0758] Exemplarily, the terminal, the network side device, or the server can perform AI model supervision based on the configuration information for AI model supervision.

[0759] Optionally, the trigger condition of AI model supervision includes at least one of:

[0760] The result of AI model inference does not meet the accuracy requirement;

[0761] At least one indicator of AI model inference does not meet the requirement;

[0762] The indicator of model supervision does not meet the requirement;

[0763] The timer for AI model supervision is timed out;

[0764] The terminal switches a cell, or switches a TRP, or switches a beam;

[0765] The AI model inference fails;

[0766] The AI model continuously fails T times of inference, where T is a positive integer;

[0767] The number of times of AI model inference failure reaches a preset number of times;

[0768] The AI model inference is used;

[0769] The terminal moves to a new cell, or a tracking area, or a geographic location;

[0770] The moving speed of the terminal is greater than or equal to a thirteenth threshold, or the acceleration of the terminal is greater than or equal to a fourteenth threshold;

[0771] The external environment of the inference device of the AI model changes.

[0772] The at least one indicator of AI model inference can include at least one of a complexity of the AI model, a time delay of AI model inference, a success rate of AI model inference, a reliability of the result output by the AI model, and the like.

[0773] The indicator of model supervision can include at least one of an error between a predicted value of the AI model and a real value, and a performance indicator of a communication system. The performance indicator of the communication system can include at least one of a transmission time delay, a throughput, and the like.

[0774] Optionally, the method further includes at least one of:

[0775] The first device sends AI related capability information of the first device;

[0776] The first device determines AI-related capability information of the second device;

[0777] The AI-related capability information is used to indicate at least one of the following:

[0778] Possessing or not possessing the capability of training an AI model for obtaining the first information;

[0779] Possessing or not possessing the capability of obtaining the first information through the AI model;

[0780] Possessing or not possessing the capability of sending first auxiliary information, the first auxiliary information being used to obtain the first information through the AI model;

[0781] Possessing or not possessing the capability of sending second auxiliary information, the second auxiliary information being used to train the AI model for obtaining the first information.

[0782] In an embodiment, the first device can send AI-related capability information of the first device to the second device. For example, in the case that the AI-related capability information of the first device indicates that the first device possesses the capability of training an AI model for predicting the first information, the second device can determine that the training of the AI model for predicting the first information is performed by the first device. In the case that the AI-related capability information of the first device indicates that the first device does not possess the capability of training an AI model for predicting the first information, the second device can determine to perform the training of the AI model for predicting the first information.

[0783] In another embodiment, the first device can determine AI-related capability information of the second device. For example, in the case that the AI-related capability information of the second device indicates that the second device possesses the capability of training an AI model for predicting the first information, the first device can determine that the training of the AI model for predicting the first information is performed by the second device. In the case that the AI-related capability information of the second device indicates that the second device does not possess the capability of training an AI model for predicting the first information, the first device can determine to perform the training of the AI model for predicting the first information.

[0784] It can be understood that before a terminal, a network-side device or a server performs AI model training, supervision or inference, the related capability of the terminal, the network-side device or the server needs to be defined, and a method of determining the related capability is given, which is helpful for each node to flexibly implement corresponding features, and is helpful for the feature implementation between nodes.

[0785] Optionally, the first device determines AI-related capability information of the second device, comprising:

[0786] The first device determines AI-related capability information of the second device based on at least one of the following:

[0787] a device type of the second device;

[0788] AI-related capability information indicated by a reference signal;

[0789] AI-related capability information carried by control information sent by the second device;

[0790] AI-related capability information carried by RRC signaling sent by the second device;

[0791] AI-related capability information carried by an interface message between the first device and the second device.

[0792] For example, the first device can determine the AI-related capability information of the second device based on the device type of the second device, for example, different AI-related capabilities are introduced for different terminal types (e.g., Reduced Capability (RedCap), Internet of Things (IoT), etc.), or different AI-related capabilities can be introduced for different network types (e.g., Non Terrestrial Network (NTN), Terrestrial Network (TN), etc.).

[0793] For AI-related capability information indicated by a reference signal, for example, indicating the capability of AI model training or AI model inference through RACH resources or SRS resources, etc.

[0794] The control information can include uplink control information or physical layer control information (e.g., Uplink Control Information (UCI) reported by the terminal to the network, etc.).

[0795] The interface message between the first device and the second device can be a specific interface message, which can be only for a specific AI model, or can be for all AI models. For example, in the case where one of the first device and the second device is a terminal and the other is a network side device, the interface message between the first device and the second device can be an interface message between the terminal and the network side device. In the case where one of the first device and the second device is a terminal and the other is a server, the interface message between the first device and the second device can be an interface message between the terminal and the server. In the case where one of the first device and the second device is a network side device and the other is a server, the interface message between the first device and the second device can be an interface message between the network side device and the server.

[0796] It can be understood that the second device can determine the AI-related capability information of the first device based on at least one of the following:

[0797] The device type of the first device;

[0798] The AI-related capability information indicated by the reference signal;

[0799] The AI-related capability information carried by the control information sent by the first device;

[0800] The AI-related capability information carried by the RRC signaling sent by the first device;

[0801] The AI-related capability information carried by the interface message between the first device and the second device.

[0802] In some optional embodiments, if the terminal performs AI model training / inference, the type of the terminal needs to be considered, and different types of terminals can have different AI model training / inference capabilities.

[0803] For example, for different types of terminals, the input information for model training / inference is different. For example, for a terminal device with weak capability, the input information for model training should be less.

[0804] For example, for different types of terminals, the labels for model training are different.

[0805] For example, for different types of terminals, the execution mode of model training is different. For example, for a terminal device with weak capability, it can be considered to only perform model training on the network side, or the terminal side only performs a small part of joint model training, such as model training involving user privacy data can be performed on the terminal side.

[0806] For example, for different types of terminals, the AI model for model training is different. For example, a terminal device with weak capability may not be able to apply a too complex AI model.

[0807] As can be seen from the above, by using the transmission method provided in the embodiments of the present application, the full-duplex transmission mode or full-duplex transmission resource can be selected based on the AI model, which ensures the resource utilization rate, and at the same time, the full-duplex transmission mode or full-duplex transmission resource can be reasonably utilized to reduce the terminal energy consumption, ensure the performance of full-duplex transmission, and reduce the transmission delay.

[0808] Please refer to FIG. 7, which is a flowchart of a transmission method provided by an embodiment of the present application. The method can be performed by a second device, as shown in FIG. 7, and includes the following steps:

[0809] Step 701, the second device performs a second operation, and the second operation includes at least one of the following:

[0810] obtaining first information based on the AI model, and sending the first information to the first device;

[0811] receiving second information from the first device, the second information comprising at least one of the following: the first information, at least part of the input information of the AI model;

[0812] training at least part of the AI model;

[0813] sending model information, the model information being used to determine at least part of the AI model;

[0814] sending a supervision result of the AI model;

[0815] sending indication information for triggering AI model training;

[0816] sending indication information for triggering AI model inference;

[0817] wherein the AI model is used to predict at least one of the following:

[0818] a first transmission mode, the first transmission mode comprising a half-duplex transmission mode or a full-duplex transmission mode;

[0819] at least one spatial domain information;

[0820] at least one first performance information, the first performance information being performance information related to transmission in the full-duplex transmission mode;

[0821] at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission;

[0822] at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission;

[0823] at least one resource of a guard band;

[0824] at least one related parameter of uplink transmission power;

[0825] at least one interference information.

[0826] Optionally, the spatial domain information comprises at least one of the following: spatial domain information corresponding to downlink transmission, spatial domain information corresponding to uplink transmission.

[0827] Optionally, the first performance information comprises at least one of the following:

[0828] a probability of successful transmission in the full-duplex transmission mode;

[0829] a probability of failed transmission in the full-duplex transmission mode;

[0830] a number of times of failed transmission in the full-duplex transmission mode.

[0831] Optionally, the first information further comprises at least one probability information.

[0832] The probability information corresponds to at least one of the following: at least one spatial domain information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one resource of a guard band, and at least one related parameter of an uplink transmission power.

[0833] Optionally, the input information of the AI model comprises at least one of the following:

[0834] Signal information, distance information, path loss information, second performance information, maximum transmission power of uplink transmission, region information, frequency domain information, beam information, time delay information, service related information, state information of the terminal, state information of the network side device, state information of the satellite, perception information, non-terrestrial network (NTN) base station information, channel information, and time information; wherein the second performance information is performance information related to transmission in a full duplex transmission mode.

[0835] Optionally, the signal information comprises at least one of the following: signal strength information, signal quality information, and interference signal strength information.

[0836] Optionally, the signal strength information comprises at least one of the following:

[0837] Received strength information of an uplink signal between the first device and the second device;

[0838] Received strength information of a downlink signal between the first device and the second device;

[0839] Or,

[0840] The signal quality information comprises at least one of the following:

[0841] Signal quality information of an uplink signal between the first device and the second device;

[0842] Signal quality information of a downlink signal between the first device and the second device;

[0843] Or,

[0844] The interference signal strength information comprises at least one of the following:

[0845] Self-interference strength information of the first device;

[0846] Mutual interference strength information of the first device;

[0847] Self-interference strength information of the second device;

[0848] Mutual interference strength information of the second device.

[0849] Optionally, the distance information comprises at least one of:

[0850] a distance between the first terminal and a network node of the first cell;

[0851] a distance between a network node of the source cell and a network node of the target cell;

[0852] a distance between a network node of the Pcell and a network node of the Scell;

[0853] a distance between the first terminal and the second terminal;

[0854] or,

[0855] Optionally, the path loss information comprises at least one of:

[0856] a path loss between the first terminal and a network node of the first cell;

[0857] a path loss between a network node of the source cell and a network node of the target cell;

[0858] a path loss between a network node of the Pcell and a network node of the Scell;

[0859] wherein the first cell comprises at least one of: the source cell, the target cell, a currently camped cell or a currently accessed cell, the Pcell, the Scell; and the first terminal and the second terminal are both terminals of the first cell.

[0860] Optionally, the second performance information comprises at least one of:

[0861] a number of downlink signal reception failures of full-duplex transmission under a certain time domain resource;

[0862] a number of downlink signal reception failures of full-duplex transmission under a certain frequency domain resource;

[0863] a number of downlink signal reception failures of full-duplex transmission under a certain spatial domain information;

[0864] a number of downlink signal reception failures of full-duplex transmission under a certain uplink transmission power;

[0865] a number of downlink signal reception failures of full-duplex transmission under a certain cell signal strength;

[0866] a number of downlink signal reception failures of full-duplex transmission under a certain interference signal strength;

[0867] a number of downlink signal reception failures of full-duplex transmission under a certain guard band resource.

[0868] Optionally, the service-related information comprises at least one of the following:

[0869] a load condition of at least one cell of the first cell;

[0870] an interference condition of at least one cell of the first cell;

[0871] a load condition corresponding to at least one spatial feature of the first cell;

[0872] an interference condition corresponding to at least one spatial feature of the first cell;

[0873] a load condition corresponding to at least one carrier or frequency point of the first cell;

[0874] an interference condition corresponding to at least one carrier or frequency point of the first cell;

[0875] The first cell comprises at least one of the following: a source cell, a target cell, a current camped cell or a current accessed cell, a Pcell, a Scell; the spatial feature comprises at least one of the following: an SSB, a TCI, a TRP, a beam.

[0876] Optionally, the state information of the terminal comprises at least one of the following: location information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption condition of the terminal, power condition of the terminal, operator information supported by the terminal, network type information supported by the terminal, panel orientation information of the terminal, type of the terminal, network scene information of the terminal, environment information in which the terminal is located;

[0877] Or,

[0878] The state information of the network-side device comprises at least one of the following: transmission power information of the network-side device, location information of the network-side device, panel orientation information of the network-side device, energy consumption condition of the network-side device, power condition of the network-side device, environment information in which the network-side device is located;

[0879] Or,

[0880] The state information of the satellite comprises at least one of the following: panel orientation information of the satellite, moving speed of the satellite, moving direction of the satellite.

[0881] Optionally, the method further comprises:

[0882] The second device sends first configuration information to the first device;

[0883] The first configuration information comprises at least one of the following:

[0884] an AI model or an AI model identifier;

[0885] an application range of AI model inference;

[0886] a cycle of AI model inference;

[0887] a validity duration of AI model inference;

[0888] a triggering condition of AI model inference;

[0889] a configuration parameter of the AI model, the configuration parameter of the AI model comprising at least one of: input information of the AI model, output information of the AI model, a type of the input information of the AI model, a type of the output information of the AI model;

[0890] first indication information, used for indicating whether joint inference is supported or is required.

[0891] Optionally, the method further comprises:

[0892] the second device sends second indication information to the first device, the second indication information being used for indicating activation information or deactivation information of the AI model.

[0893] Optionally, the triggering condition of using the AI model for inference comprises at least one of:

[0894] a timer timeout for triggering AI inference;

[0895] selection of transmission based on full-duplex transmission configuration;

[0896] a failure probability corresponding to full-duplex transmission is greater than or equal to a first threshold;

[0897] an uplink transmission power corresponding to full-duplex transmission is greater than or equal to a second threshold, or the uplink transmission power corresponding to full-duplex transmission reaches a maximum transmission power;

[0898] an interference signal strength corresponding to full-duplex transmission is greater than or equal to a third threshold;

[0899] cell or TRP reselection by the terminal;

[0900] cell or TRP switching by the terminal;

[0901] service arrival;

[0902] receiving indication information used for indicating AI inference;

[0903] a change in a location of the terminal or a change in a movement parameter of the terminal;

[0904] a change in spatial information of the terminal or a change in a transmission filter.

[0905] Optionally, the condition or event triggering AI model training comprises at least one of:

[0906] a timer timeout for triggering AI model training;

[0907] a TAG related timer timeout;

[0908] receiving indication information indicating AI training;

[0909] the terminal accesses a new cell;

[0910] the terminal switches a frequency point or a frequency band;

[0911] the terminal switches an operator or a public land mobile network (PLMN);

[0912] AI model inference fails;

[0913] AI model inference fails P times consecutively, P being a positive integer;

[0914] a number of times of AI model inference failure reaches a fourth threshold;

[0915] AI model inference is used;

[0916] the terminal moves to a new cell or a tracking area or a geographic location;

[0917] a moving speed of the terminal changes or a change amount of the moving speed of the terminal is greater than or equal to a fifth threshold;

[0918] a RSRP measurement value of the terminal changes or a change amount of the RSRP measurement value of the terminal is greater than or equal to a sixth threshold;

[0919] a duration of a timer timeout for AI model training reaches a first duration;

[0920] K times of model supervision occur or S times of consecutive model supervision occur, K and S being positive integers;

[0921] an external environment of the terminal changes;

[0922] a moving speed of the terminal is greater than or equal to a seventh threshold or an acceleration of the terminal is greater than or equal to an eighth threshold;

[0923] a position of the terminal changes or a change amount of the position of the terminal is greater than or equal to a ninth threshold;

[0924] a moving parameter of the terminal changes;

[0925] spatial information of the terminal changes or a spatial transmission filter of the terminal changes;

[0926] a full-duplex transmission configuration is configured by a network side device;

[0927] The failure probability corresponding to the full-duplex transmission is greater than or equal to a tenth threshold;

[0928] The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to an eleventh threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches a maximum transmission power;

[0929] The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold;

[0930] The terminal performs cell or TRP switching;

[0931] The terminal performs cell or TRP reselection;

[0932] The service arrives;

[0933] Receiving indication information for indicating that the full-duplex transmission information is determined based on an AI model.

[0934] Optionally, the label for AI model training includes at least one of the following:

[0935] Obtaining or not obtaining the first information satisfying the performance requirement;

[0936] The number of obtained first information;

[0937] The duration of AI model training;

[0938] The energy consumption of AI model training;

[0939] The first information required for transmission between the terminal and the network node of the first cell.

[0940] Optionally, the configuration information for AI model supervision includes at least one of the following:

[0941] The AI model or AI model identifier that needs to be supervised;

[0942] The period of model supervision;

[0943] The duration of model supervision;

[0944] The detection window related information of model supervision;

[0945] The trigger condition of model supervision;

[0946] The index of model supervision;

[0947] The label of model supervision.

[0948] Optionally, the trigger condition of AI model supervision includes at least one of the following:

[0949] The result of AI model inference does not meet the accuracy requirement;

[0950] At least one index of AI model inference does not meet requirements;

[0951] An index of model supervision does not meet requirements;

[0952] Timer timeout for AI model supervision;

[0953] Terminal switches cells or switches TRPs or switches beams;

[0954] AI model inference fails;

[0955] AI model continuous inference fails T times, T is a positive integer;

[0956] The number of times of AI model inference failure reaches a third preset number;

[0957] AI model inference is used;

[0958] The terminal moves to a new cell or tracking area or geographic location;

[0959] The moving speed of the terminal is greater than or equal to a thirteenth threshold, or the acceleration of the terminal is greater than or equal to a fourteenth threshold;

[0960] The external environment of the inference device of the AI model changes.

[0961] Optionally, the method further comprises:

[0962] The second device receives AI-related capability information of the first device;

[0963] The AI-related capability information is used to indicate at least one of the following:

[0964] Possessing or not possessing the capability of training an AI model for obtaining the first information;

[0965] Possessing or not possessing the capability of obtaining the first information through the AI model;

[0966] Possessing or not possessing the capability of sending first auxiliary information for obtaining the first information through the AI model;

[0967] Possessing or not possessing the capability of sending second auxiliary information for training the AI model for obtaining the first information.

[0968] It should be noted that the implementation mode of the embodiment can refer to the related description of the embodiment shown in FIG. 6, which will not be repeated here.

[0969] It should be noted that the transmission method provided by the embodiment of the application can be executed by the transmission device. In the embodiment of the application, the transmission device executes the transmission method, and the transmission device provided by the embodiment of the application is described.

[0970] Embodiments of the present application provide a transmission device. As an example, the transmission device can be a communication device or a component in a communication device, such as a chip. The communication device can be a terminal, a network-side device, a server, or the like. For example, the terminal can include, but is not limited to, the types of terminals 11 listed, and the network-side device can include, but is not limited to, the types of network-side devices 12 listed, and embodiments of the present application are not limited in this regard.

[0971] The transmission device includes a receiving module, a sending module, and a processing module. The receiving module, the sending module, and the processing module can be implemented by software or by hardware. When implemented by hardware, the processing module can be implemented by a processor. For example, the processor can include a general-purpose processor, a special-purpose processor, or the like, such as a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), an artificial intelligent (AI) processor, a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a network processor (NP), a field programmable gate array (FPGA), or other programmable logic devices, a gate circuit, a transistor, a discrete hardware component, or the like. The receiving module and the sending module can be implemented by a communication interface, which can include one or more of a transceiver, a pin, a circuit, a bus, a radio frequency unit, or the like.

[0972] Specifically, referring to FIG. 8, when the transmission device is a first device or a component in the first device, the transmission device 800 includes a processing module 801 configured to obtain first information, the first information being information obtained based on an artificial intelligent (AI) model; and a transceiver module 802 configured to perform first transmission based on the first information, the first transmission corresponding to a half-duplex transmission mode or a full-duplex transmission mode.

[0973] The first information includes at least one of the following:

[0974] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0975] At least one spatial domain information.

[0976] at least one first performance information, the first performance information being performance information related to transmission in the full-duplex transmission mode;

[0977] at least one first transmission parameter, the first transmission parameter being a transmission parameter of the uplink transmission;

[0978] at least one second transmission parameter, the second transmission parameter being a transmission parameter of the downlink transmission;

[0979] at least one resource of a guard band;

[0980] at least one related parameter of an uplink transmit power;

[0981] at least one interference information.

[0982] Optionally, the processing module is specifically configured to:

[0983] receive the first information from the second device;

[0984] or,

[0985] obtain the first information based on the AI model.

[0986] Optionally, the spatial domain information comprises at least one of: spatial domain information corresponding to the downlink transmission, and spatial domain information corresponding to the uplink transmission.

[0987] Optionally, the first performance information comprises at least one of:

[0988] a probability of successful transmission in the full-duplex transmission mode;

[0989] a probability of failed transmission in the full-duplex transmission mode;

[0990] a number of times of failed transmission in the full-duplex transmission mode.

[0991] Optionally, the first transmission parameter comprises at least one of: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, and a number of retransmissions.

[0992] or,

[0993] the second transmission parameter comprises at least one of: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, and a number of retransmissions.

[0994] Optionally, the resource of the guard band comprises at least one of: a frequency domain position of the guard band, and a frequency domain size of the guard band.

[0995] Optionally, the related parameter of the uplink transmit power comprises at least one of: a target uplink transmit power, a target receive power value, a maximum transmit power, a power boosting value, and a power backoff value.

[0996] Optionally, the interference information comprises at least one of: interference intensity information, interference signal information.

[0997] Optionally, the interference intensity information comprises at least one of: self-interference intensity, mutual interference intensity, and indication information indicating whether the interference intensity meets a corresponding threshold.

[0998] Optionally, the interference signal information comprises at least one of: reverse signals of the at least one transmitted signal, and pre-processing information corresponding to the at least one transmitted signal.

[0999] Optionally, the first information further comprises at least one probability information.

[1000] The probability information corresponds to at least one of: at least one spatial domain information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one resource of a guard band, and at least one related parameter of an uplink transmission power.

[1001] Optionally, the input information of the AI model comprises at least one of:

[1002] signal information, distance information, path loss information, second performance information, maximum transmission power of uplink transmission, region information, frequency domain information, beam information, time delay information, service related information, state information of the terminal, state information of the network side device, state information of the satellite, perception information, non-terrestrial network (NTN) base station information, channel information, and time information; the second performance information is performance information related to transmission in a full-duplex transmission mode.

[1003] Optionally, the signal information comprises at least one of: signal intensity information, signal quality information, and interference signal intensity information.

[1004] Optionally, the signal intensity information comprises at least one of:

[1005] received intensity information of an uplink signal between the first device and the second device;

[1006] received intensity information of a downlink signal between the first device and the second device;

[1007] or

[1008] The signal quality information comprises at least one of:

[1009] signal quality information of an uplink signal between the first device and the second device;

[1010] signal quality information of a downlink signal between the first device and the second device;

[1011] or

[1012] The interference signal strength information comprises at least one of:

[1013] Self-interference strength information of the first device;

[1014] Mutual-interference strength information of the first device;

[1015] Self-interference strength information of the second device;

[1016] Mutual-interference strength information of the second device.

[1017] Optionally, the distance information comprises at least one of:

[1018] A distance between the first terminal and a network node of the first cell;

[1019] A distance between a network node of the source cell and a network node of the target cell;

[1020] A distance between a network node of the Pcell and a network node of the Scell;

[1021] A distance between the first terminal and the second terminal;

[1022] Or,

[1023] The path loss information comprises at least one of:

[1024] A path loss between the first terminal and a network node of the first cell;

[1025] A path loss between a network node of the source cell and a network node of the target cell;

[1026] A path loss between a network node of the Pcell and a network node of the Scell;

[1027] The first cell comprises at least one of: the source cell, the target cell, a currently camped cell or a currently accessed cell, the Pcell, the Scell; the first terminal and the second terminal are both terminals of the first cell.

[1028] Optionally, the second performance information comprises at least one of:

[1029] A number of downlink signal reception failures of full-duplex transmission under a certain time domain resource;

[1030] A number of downlink signal reception failures of full-duplex transmission under a certain frequency domain resource;

[1031] A number of downlink signal reception failures of full-duplex transmission under a certain spatial domain information;

[1032] A number of downlink signal reception failures of full-duplex transmission under a certain uplink transmission power;

[1033] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[1034] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[1035] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

[1036] Optionally, the area information includes at least one of the following: Transmitter / Receiver Point (TRP) identifier, TRP group identifier, cell identifier, cell group identifier, Timing Advance Group (TAG) identifier, Tracking Area (TA) identifier, and Radio Access Network Notification Area (RAN) identifier.

[1037] Optionally, business-related information includes at least one of the following:

[1038] Load status of at least one cell in the first cell;

[1039] Interference situation in at least one cell of the first cell;

[1040] The load status corresponding to at least one spatial feature of the first cell;

[1041] Interference situation corresponding to at least one spatial feature of the first cell;

[1042] The load status of at least one carrier or frequency point in the first cell;

[1043] Interference situation corresponding to at least one carrier and frequency point of the first cell;

[1044] The first cell includes at least one of the following: source cell, target cell, currently camped cell or currently accessed cell, Pcell, Scell; the spatial characteristics include at least one of the following: SSB, TCI, TRP, beam.

[1045] Optionally, the terminal's status information includes at least one of the following: the terminal's location information, the terminal's distribution information, the terminal's direction of movement, the terminal's speed of movement, the terminal's energy consumption status, the terminal's battery status, the terminal's supported operator information, the terminal's supported network type information, the terminal's panel orientation information, the terminal's type, the terminal's network scenario information, and the environment information where the terminal is located.

[1046] or,

[1047] The status information of the network-side device includes at least one of the following: the transmission power information of the network-side device, the location information of the network-side device, the panel orientation information of the network-side device, the energy consumption status of the network-side device, the power status of the network-side device, and the environmental information of the network-side device.

[1048] Or,

[1049] The state information of the satellite includes at least one of panel orientation information of the satellite, a moving speed of the satellite, and a moving direction of the satellite.

[1050] Optionally, the processing module is further configured to:

[1051] obtain first configuration information;

[1052] The first configuration information includes at least one of the following:

[1053] an AI model or an AI model identifier;

[1054] an application range of AI model inference;

[1055] a cycle of AI model inference;

[1056] a validity duration of AI model inference;

[1057] a trigger condition of AI model inference;

[1058] a configuration parameter of the AI model, the configuration parameter of the AI model including at least one of input information of the AI model, output information of the AI model, a type of the input information of the AI model, and a type of the output information of the AI model;

[1059] first indication information, used for indicating whether joint inference is supported or is needed.

[1060] Optionally, the processing module is further configured to:

[1061] obtain second indication information, the second indication information being used for indicating activation information or deactivation information of the AI model;

[1062] The first device activates or deactivates the AI model according to the second indication information.

[1063] Optionally, the trigger condition of using the AI model for inference includes at least one of the following:

[1064] a timer timeout for triggering AI inference;

[1065] selecting to perform transmission based on a full-duplex transmission configuration;

[1066] a failure probability corresponding to full-duplex transmission being greater than or equal to a first threshold;

[1067] an uplink transmission power corresponding to full-duplex transmission being greater than or equal to a second threshold, or the uplink transmission power reaching a maximum transmission power;

[1068] an interference signal strength corresponding to full-duplex transmission being greater than or equal to a third threshold;

[1069] The terminal performs cell or TRP reselection;

[1070] The terminal performs cell or TRP switching;

[1071] The service arrives;

[1072] The indication information for indicating to perform AI inference is received;

[1073] The location of the terminal changes or the movement parameter of the terminal changes;

[1074] The spatial information of the terminal changes or the transmission filter changes.

[1075] Optionally, the processing module is further configured to:

[1076] Perform a first operation, the first operation comprising at least one of:

[1077] Send second information, the second information comprising at least one of: the first information, at least part of the input information of the AI model, and the state information of the first device;

[1078] Fall back to determining the first information in a non-AI manner;

[1079] Trigger adjustment of the AI model;

[1080] Trigger training of the AI model;

[1081] Trigger supervision of the AI model.

[1082] Optionally, the trigger condition of the first operation comprises at least one of:

[1083] The first information satisfying the performance requirement is still not obtained after using the AI model to infer for more than M time length;

[1084] The AI inference is not successfully completed using the AI model, or the AI inference is successfully completed using the AI model;

[1085] The AI model is used to perform N times of AI inference;

[1086] Wherein, M and N are positive integers.

[1087] Optionally, the processing module is further configured to train at least part of the AI models;

[1088] Or,

[1089] The transceiver module is further configured to receive model information, the model information being used to determine at least part of the AI models.

[1090] Optionally, the condition or event triggering the training of the AI model comprises at least one of:

[1091] a timer timeout for triggering AI model training;

[1092] a TAG related timer timeout;

[1093] receiving indication information indicating AI training;

[1094] the terminal accesses a new cell;

[1095] the terminal switches a frequency point or a frequency band;

[1096] the terminal switches an operator or a public land mobile network (PLMN);

[1097] AI model inference fails;

[1098] AI model inference fails P times in succession, P being a positive integer;

[1099] the number of times of AI model inference failure reaches a fourth threshold;

[1100] AI model inference is used;

[1101] the terminal moves to a new cell or a tracking area or a geographic location;

[1102] a change in the moving speed of the terminal occurs, or a change amount of the moving speed of the terminal is greater than or equal to a fifth threshold;

[1103] a change in the RSRP measurement value of the terminal occurs, or a change amount of the RSRP measurement value of the terminal is greater than or equal to a sixth threshold;

[1104] a duration of a timer timeout for AI model training reaches a first duration;

[1105] K times of model supervision occur or S times of model supervision in succession occur, K and S being positive integers;

[1106] a change in the external environment of the terminal occurs;

[1107] the moving speed of the terminal is greater than or equal to a seventh threshold, or the acceleration of the terminal is greater than or equal to an eighth threshold;

[1108] a change in the position of the terminal occurs, or a change amount of the position of the terminal is greater than or equal to a ninth threshold;

[1109] a change in the moving parameter of the terminal occurs;

[1110] a change in the spatial information of the terminal occurs or a change in the spatial transmission filter of the terminal occurs;

[1111] a full-duplex transmission configuration is configured by a network side device;

[1112] The failure probability corresponding to the full-duplex transmission is greater than or equal to a tenth threshold;

[1113] The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to an eleventh threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches a maximum transmission power;

[1114] The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold;

[1115] The terminal performs cell or TRP switching;

[1116] The terminal performs cell or TRP reselection;

[1117] The service arrives;

[1118] Receiving indication information for indicating that the full-duplex transmission information is determined based on the AI model.

[1119] Optionally, the label for AI model training includes at least one of the following:

[1120] Obtaining or not obtaining the first information satisfying the performance requirement;

[1121] The number of obtained first information;

[1122] The duration of AI model training;

[1123] The energy consumption of AI model training;

[1124] The first information required for transmission between the terminal and the network node of the first cell.

[1125] Optionally, the processing module is further configured to supervise the AI model;

[1126] Or,

[1127] The transceiver module is further configured to receive the model supervision result of the AI model.

[1128] Optionally, the configuration information for AI model supervision includes at least one of the following:

[1129] The AI model or AI model identifier that needs to be supervised;

[1130] The period of model supervision;

[1131] The duration of model supervision;

[1132] The detection window related information of model supervision;

[1133] The trigger condition of model supervision;

[1134] The index of model supervision;

[1135] The label of model supervision.

[1136] Optionally, the trigger condition of the AI model supervision comprises at least one of the following:

[1137] The result of the AI model inference does not meet the accuracy requirement;

[1138] At least one indicator of the AI model inference does not meet the requirement;

[1139] The indicator of the model supervision does not meet the requirement;

[1140] The timer for AI model supervision times out;

[1141] The terminal switches a cell or switches a TRP or switches a beam;

[1142] The AI model inference fails;

[1143] The AI model continuously fails T times of inference, T being a positive integer;

[1144] The number of times of AI model inference failure reaches a third preset number;

[1145] The AI model inference is used;

[1146] The terminal moves to a new cell or tracking area or geographic location;

[1147] The moving speed of the terminal is greater than or equal to a thirteenth threshold, or the acceleration of the terminal is greater than or equal to a fourteenth threshold;

[1148] The external environment of the inference device of the AI model changes.

[1149] Optionally, the transceiver module is further configured to send AI-related capability information of the first device;

[1150] and / or,

[1151] The processing module is further configured to determine AI-related capability information of the second device;

[1152] The AI-related capability information is used to indicate at least one of the following:

[1153] Possessing or not possessing the capability of training the AI model for obtaining the first information;

[1154] Possessing or not possessing the capability of obtaining the first information through the AI model;

[1155] Possessing or not possessing the capability of sending first auxiliary information, the first auxiliary information being used to obtain the first information through the AI model;

[1156] Possessing or not possessing the capability of sending second auxiliary information, the second auxiliary information being used to train the AI model for obtaining the first information.

[1157] Optionally, the processing module is specifically configured to:

[1158] determine the AI-related capability information of the second device based on at least one of the following:

[1159] a device type of the second device;

[1160] AI-related capability information indicated by a reference signal;

[1161] AI-related capability information carried by control information sent by the second device;

[1162] AI-related capability information carried by RRC signaling sent by the second device;

[1163] AI-related capability information carried by an interface message between the first device and the second device.

[1164] The transmission apparatus provided in the embodiments of the present application can implement each process achieved by the method embodiment of FIG. 6 and achieve the same technical effects. To avoid repetition, details are not described herein.

[1165] Referring to FIG. 9, when the transmission apparatus is a network-side device or a component in the network-side device, the transmission apparatus 900 includes a processing module 901 configured to perform a second operation, and the second operation includes at least one of the following:

[1166] obtain first information based on an AI model, and send the first information to the first device;

[1167] receive second information from the first device, and the second information includes at least one of the following: the first information, at least part of input information of the AI model;

[1168] train at least part of the AI model;

[1169] send model information, and the model information is used to determine at least part of the AI model;

[1170] send a supervision result of the AI model;

[1171] send indication information used to trigger training of the AI model;

[1172] send indication information used to trigger inference of the AI model;

[1173] The AI model is used to predict at least one of the following:

[1174] a first transmission mode, and the first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode;

[1175] at least one spatial domain information;

[1176] at least one first performance information, the first performance information being performance information related to transmission in the full-duplex transmission mode;

[1177] at least one first transmission parameter, the first transmission parameter being a transmission parameter of the uplink transmission;

[1178] at least one second transmission parameter, the second transmission parameter being a transmission parameter of the downlink transmission;

[1179] at least one guard band resource;

[1180] at least one uplink transmit power related parameter;

[1181] at least one interference information.

[1182] Optionally, the spatial domain information comprises at least one of: spatial domain information corresponding to the downlink transmission, spatial domain information corresponding to the uplink transmission.

[1183] Optionally, the first performance information comprises at least one of:

[1184] a probability of successful transmission in the full-duplex transmission mode;

[1185] a probability of failed transmission in the full-duplex transmission mode;

[1186] a number of failed transmissions in the full-duplex transmission mode.

[1187] Optionally, the first information further comprises at least one probability information;

[1188] wherein the probability information corresponds to at least one of: the at least one spatial domain information, the at least one transmission mode, the at least one first transmission parameter, the at least one second transmission parameter, the at least one guard band resource, the at least one uplink transmit power related parameter.

[1189] Optionally, the input information of the AI model comprises at least one of:

[1190] signal information, distance information, path loss information, second performance information, maximum transmit power of the uplink transmission, region information, frequency domain information, beam information, time delay information, service related information, state information of the terminal, state information of the network side device, state information of the satellite, perception information, non-terrestrial network NTN base station information, channel information, time information; wherein the second performance information is performance information related to transmission in the full-duplex transmission mode.

[1191] Optionally, the signal information comprises at least one of: signal strength information, signal quality information, interference signal strength information.

[1192] Optionally, the signal strength information comprises at least one of:

[1193] received strength information of an uplink signal between the first device and the second device;

[1194] received strength information of a downlink signal between the first device and the second device;

[1195] or,

[1196] the signal quality information comprises at least one of:

[1197] signal quality information of an uplink signal between the first device and the second device;

[1198] signal quality information of a downlink signal between the first device and the second device;

[1199] or,

[1200] the interference signal strength information comprises at least one of:

[1201] self-interference strength information of the first device;

[1202] mutual-interference strength information of the first device;

[1203] self-interference strength information of the second device;

[1204] mutual-interference strength information of the second device.

[1205] Optionally, the distance information comprises at least one of:

[1206] a distance between the first terminal and a network node of the first cell;

[1207] a distance between a network node of the source cell and a network node of the target cell;

[1208] a distance between a network node of a primary cell Pcell and a network node of a secondary cell Scell;

[1209] a distance between the first terminal and the second terminal;

[1210] or,

[1211] the path loss information comprises at least one of:

[1212] a path loss between the first terminal and a network node of the first cell;

[1213] a path loss between a network node of the source cell and a network node of the target cell;

[1214] a path loss between a network node of the Pcell and a network node of the Scell;

[1215] The first cell includes at least one of the following: a source cell, a target cell, a currently camped cell or a currently accessed cell, a Pcell, and a Scell.

[1216] Optionally, the second performance information includes at least one of the following:

[1217] The number of times of receiving a downlink signal of full-duplex transmission under a specific time domain resource fails;

[1218] The number of times of receiving a downlink signal of full-duplex transmission under a specific frequency domain resource fails;

[1219] The number of times of receiving a downlink signal of full-duplex transmission under a specific spatial domain information fails;

[1220] The number of times of receiving a downlink signal of full-duplex transmission under a specific uplink transmission power fails;

[1221] The number of times of receiving a downlink signal of full-duplex transmission under a specific cell signal strength fails;

[1222] The number of times of receiving a downlink signal of full-duplex transmission under a specific interference signal strength fails;

[1223] The number of times of receiving a downlink signal of full-duplex transmission under a specific guard band resource fails.

[1224] Optionally, the service related information includes at least one of the following:

[1225] The load condition of at least one cell of the first cell;

[1226] The interference condition of at least one cell of the first cell;

[1227] The load condition corresponding to at least one spatial domain feature of the first cell;

[1228] The interference condition corresponding to at least one spatial domain feature of the first cell;

[1229] The load condition corresponding to at least one carrier or frequency point of the first cell;

[1230] The interference condition corresponding to at least one carrier or frequency point of the first cell;

[1231] The first cell includes at least one of the following: a source cell, a target cell, a currently camped cell or a currently accessed cell, a Pcell, and a Scell.

[1232] Optionally, the state information of the terminal includes at least one of the following: position information of the terminal, distribution information of the terminal, moving direction of the terminal, moving speed of the terminal, energy consumption status of the terminal, power status of the terminal, operator information supported by the terminal, network type information supported by the terminal, panel orientation information of the terminal, type of the terminal, network scene information of the terminal, environment information in which the terminal is located;

[1233] Or,

[1234] The state information of the network side device includes at least one of the following: transmission power information of the network side device, position information of the network side device, panel orientation information of the network side device, energy consumption status of the network side device, power status of the network side device, environment information in which the network side device is located;

[1235] Or,

[1236] The state information of the satellite includes at least one of the following: panel orientation information of the satellite, moving speed of the satellite, moving direction of the satellite.

[1237] Optionally, the apparatus further includes a sending module for sending the first configuration information to the first device;

[1238] The first configuration information includes at least one of the following:

[1239] AI model or AI model identifier;

[1240] Application range of AI model inference;

[1241] Period of AI model inference;

[1242] Effective duration of AI model inference;

[1243] Triggering condition of AI model inference;

[1244] Configuration parameter of AI model, which includes at least one of the following: input information of AI model, output information of AI model, type of input information of AI model, type of output information of AI model;

[1245] First indication information for indicating whether joint inference is supported or needed.

[1246] Optionally, the apparatus further includes a sending module for sending second indication information to the first device, the second indication information being used for indicating activation information or deactivation information of the AI model.

[1247] Optionally, the triggering condition for using the AI model for inference includes at least one of the following:

[1248] Timer timeout for triggering AI inference;

[1249] transmission is selected based on a full-duplex transmission configuration;

[1250] a failure probability corresponding to the full-duplex transmission is greater than or equal to a first threshold;

[1251] an uplink transmit power corresponding to the full-duplex transmission is greater than or equal to a second threshold, or the uplink transmit power corresponding to the full-duplex transmission reaches a maximum transmit power;

[1252] an interference signal strength corresponding to the full-duplex transmission is greater than or equal to a third threshold;

[1253] the terminal performs cell or TRP reselection;

[1254] the terminal performs cell or TRP switching;

[1255] service arrival;

[1256] receiving indication information indicating to perform AI inference;

[1257] a location of the terminal changes or a movement parameter of the terminal changes;

[1258] spatial information of the terminal changes or a transmission filter changes.

[1259] Optionally, the condition or event triggering the AI model training includes at least one of the following:

[1260] a timer for triggering the AI model training expires;

[1261] a timer related to the TAG expires;

[1262] receiving indication information indicating AI training;

[1263] the terminal accesses a new cell;

[1264] the terminal switches a frequency point or a frequency band;

[1265] the terminal switches an operator or a public land mobile network (PLMN);

[1266] AI model inference fails;

[1267] AI model continuous inference fails P times, P being a positive integer;

[1268] a number of times of AI model inference failure reaches a fourth threshold;

[1269] AI model inference is used;

[1270] the terminal moves to a new cell or a tracking area or a geographic location;

[1271] A change in the moving speed of the terminal, or a change amount of the moving speed of the terminal is greater than or equal to a fifth threshold;

[1272] A change in the RSRP measurement value of the terminal, or a change amount of the RSRP measurement value of the terminal is greater than or equal to a sixth threshold;

[1273] A length of a timer timeout for AI model training reaches a first length;

[1274] K times of model supervision occur or S consecutive times of model supervision occur, K and S are positive integers;

[1275] A change in the external environment of the terminal occurs;

[1276] The moving speed of the terminal is greater than or equal to a seventh threshold, or the acceleration of the terminal is greater than or equal to an eighth threshold;

[1277] A change in the position of the terminal occurs, or a change amount of the position of the terminal is greater than or equal to a ninth threshold;

[1278] A change in the moving parameter of the terminal occurs;

[1279] A change in the spatial information of the terminal occurs or a change in the spatial transmission filter of the terminal occurs;

[1280] The network side device is configured with a full-duplex transmission configuration;

[1281] A failure probability corresponding to the full-duplex transmission is greater than or equal to a tenth threshold;

[1282] An uplink transmission power corresponding to the full-duplex transmission is greater than or equal to an eleventh threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches a maximum transmission power;

[1283] An interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold;

[1284] The terminal performs cell or TRP switching;

[1285] The terminal performs cell or TRP reselection;

[1286] A service arrives;

[1287] Indication information for indicating that the full-duplex transmission information is determined based on an AI model is received.

[1288] Optionally, the label for AI model training includes at least one of the following:

[1289] First information satisfying a performance requirement is obtained or is not obtained;

[1290] A number of obtained first information;

[1291] A length of time for AI model training;

[1292] An energy consumption for AI model training;

[1293] First information required for transmission between the terminal and a network node of the first cell.

[1294] Optionally, the configuration information for AI model supervision comprises at least one of the following:

[1295] An AI model or an AI model identifier that needs to be supervised;

[1296] A period of model supervision;

[1297] A length of time for model supervision;

[1298] Detection window related information for model supervision;

[1299] Trigger conditions for model supervision;

[1300] Indicators for model supervision;

[1301] Labels for model supervision.

[1302] Optionally, the trigger conditions for AI model supervision comprise at least one of the following:

[1303] A result of AI model inference does not meet accuracy requirements;

[1304] At least one indicator of AI model inference does not meet requirements;

[1305] Indicators for model supervision do not meet requirements;

[1306] A timer for AI model supervision expires;

[1307] The terminal switches a cell or switches a TRP or switches a beam;

[1308] AI model inference fails;

[1309] AI model continuous inference fails T times, T being a positive integer;

[1310] A number of times of AI model inference failure reaches a third preset number of times;

[1311] AI model inference is used;

[1312] The terminal moves to a new cell or a tracking area or a geographic location;

[1313] A moving speed of the terminal is greater than or equal to a thirteenth threshold, or an acceleration of the terminal is greater than or equal to a fourteenth threshold;

[1314] An external environment in which an inference device of the AI model is located changes.

[1315] Optionally, the apparatus further comprises a receiving module for receiving AI-related capability information of the first device;

[1316] The AI-related capability information is used to indicate at least one of the following:

[1317] Possessing or not possessing the capability of training an AI model used to obtain the first information;

[1318] Possessing or not possessing the capability of obtaining the first information through the AI model;

[1319] Possessing or not possessing the capability of sending first auxiliary information used to obtain the first information through the AI model;

[1320] Possessing or not possessing the capability of sending second auxiliary information used to train the AI model used to obtain the first information.

[1321] The transmission apparatus provided by the embodiments of the present application can implement each process of the method embodiment of FIG. 7 and achieve the same technical effects. To avoid repetition, details are not described herein.

[1322] As shown in FIG. 10, the embodiments of the present application further provide a communication device 1000, which comprises a processor 1001 and a memory 1002, and the memory 1002 stores programs or instructions executable on the processor 1001. For example, when the communication device 1000 is a terminal or a network side device or a server, the programs or instructions are executed by the processor 1001 to implement each step of the transmission method embodiment and achieve the same technical effects. To avoid repetition, details are not described herein.

[1323] The embodiments of the present application further provide a terminal comprising a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is configured to run programs or instructions to implement the steps in the method embodiments shown in FIG. 6 or FIG. 7. The terminal embodiment corresponds to the terminal side method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the terminal embodiment and achieve the same technical effects. The terminal can be the transmission apparatus shown in FIG. 8 or FIG. 9. Specifically, FIG. 11 is a schematic diagram of the hardware structure of a terminal according to an embodiment of the present application.

[1324] The terminal 1100 includes, but is not limited to, at least part of the components such as a radio frequency unit 1101, a network module 1102, an audio output unit 1103, an input unit 1104, a sensor 1105, a display unit 1106, a user input unit 1107, an interface unit 1108, a memory 1109, and a processor 1110.

[1325] Those skilled in the art can understand that the terminal 1100 can also include a power supply (such as a battery) for supplying power to each component, and the power supply can be logically connected to the processor 1110 through a power management system, so that the power management system can realize the functions of managing charging, discharging, and power consumption management. The terminal structure shown in FIG. 11 does not constitute a limitation on the terminal, and the terminal can include more or fewer components than those shown, or combine certain components, or different component arrangements, which will not be described here.

[1326] It should be understood that in the embodiments of the present application, the input unit 1104 can include a graphics processor 11041 and a microphone 11042. The graphics processor 11041 processes image data of a still picture or a video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 1106 can include a display panel 11061, which can be configured in the form of a liquid crystal display, an organic light-emitting diode, etc. The user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 can include two parts of a touch detection device and a touch controller. The other input devices 11072 can include, but are not limited to, a physical keyboard, function keys (such as volume control keys, on-off keys, etc.), trackballs, mice, joysticks, which will not be described here.

[1327] In the embodiments of the present application, after the radio frequency unit 1101 receives the downlink data from the network side device, it can be transmitted to the processor 1110 for processing. In addition, the radio frequency unit 1101 can send uplink data to the network side device. Generally, the radio frequency unit 1101 includes, but is not limited to, an antenna, an amplifier, a transceiver, a coupler, a low noise amplifier, a duplexer, etc.

[1328] The memory 1109 can be used to store software programs or instructions and various data. The memory 1109 can mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area can store an operating system, application programs or instructions required by at least one function (such as a sound playing function, an image playing function, etc.), and the like. In addition, the memory 1109 can include a volatile memory or a non-volatile memory. The non-volatile memory can be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a Random Access Memory (RAM), a Static RAM (SRAM), a Dynamic RAM (DRAM), a Synchronous DRAM (SDRAM), a Double Data Rate SDRAM (DDR SDRAM), an Enhanced SDRAM (ESDRAM), a Synch link DRAM (SLDRAM), and a Direct Rambus RAM (DRRAM). The memory 1109 in the embodiments of the present application includes but is not limited to these and any other suitable types of memory.

[1329] The processor 1110 can include one or more processing units; optionally, the processor 1110 integrates an application processor and a modem processor, wherein the application processor mainly processes operations related to an operating system, a user interface, and an application program, and the modem processor mainly processes wireless communication signals, such as a baseband processor. It can be understood that the modem processor can also not be integrated into the processor 1110.

[1330] The processor 1110 is configured to obtain first information, the first information being information obtained based on an artificial intelligence (AI) model; and the radio frequency unit 1101 is configured to perform first transmission based on the first information, the first transmission corresponding to a half-duplex transmission mode or a full-duplex transmission mode.

[1331] The first information includes at least one of the following:

[1332] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[1333] The at least one spatial domain information;

[1334] The at least one first performance information is performance information related to transmission in a full-duplex transmission mode.

[1335] The at least one first transmission parameter is a transmission parameter of uplink transmission.

[1336] The at least one second transmission parameter is a transmission parameter of downlink transmission.

[1337] The at least one guard band resource;

[1338] The at least one uplink transmit power related parameter;

[1339] The at least one interference information;

[1340] Or,

[1341] The processor 1110 is configured to perform a second operation, and the second operation includes at least one of the following:

[1342] Obtain first information based on an AI model, and send the first information to a first device;

[1343] Receive second information from the first device, and the second information includes at least one of the following: the first information, at least part of input information of the AI model;

[1344] Train at least part of the AI model;

[1345] Send model information, and the model information is used to determine at least part of the AI model;

[1346] Send a supervision result of the AI model;

[1347] Send indication information used to trigger AI model training;

[1348] Send indication information used to trigger AI model inference;

[1349] The AI model is used to predict at least one of the following:

[1350] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[1351] The at least one spatial domain information;

[1352] The at least one first performance information is performance information related to transmission in a full-duplex transmission mode.

[1353] at least one first transmission parameter, the first transmission parameter being a transmission parameter for uplink transmission;

[1354] at least one second transmission parameter, the second transmission parameter being a transmission parameter for downlink transmission;

[1355] at least one resource of a guard band;

[1356] at least one related parameter of uplink transmit power;

[1357] at least one interference information.

[1358] It can be understood that the implementation processes of the implementation manners mentioned in the embodiment can refer to the related descriptions of the foregoing transmission method embodiments, and achieve the same or corresponding technical effects. To avoid repetition, they will not be described here again.

[1359] The embodiment of the application further provides a network side device, which comprises a processor and a communication interface, the communication interface and the processor are coupled, and the processor is used to run programs or instructions to realize the steps of the method embodiments shown in FIG. 6 or FIG. 7. The network side device embodiment corresponds to the network side device method embodiment, and each implementation process and implementation manner of the method embodiment can be applied to the network side device embodiment and can achieve the same technical effects.

[1360] Specifically, the embodiment of the application further provides a network side device, which can be the transmission apparatus shown in FIG. 8 or FIG. 9. As shown in FIG. 12, the network side device 1200 comprises an antenna 1201, a radio frequency device 1202, a baseband device 1203, a processor 1204 and a memory 1205. The antenna 1201 is connected with the radio frequency device 1202. In the uplink direction, the radio frequency device 1202 receives information through the antenna 1201, and sends the received information to the baseband device 1203 for processing. In the downlink direction, the baseband device 1203 processes the information to be sent and sends it to the radio frequency device 1202, and the radio frequency device 1202 processes the received information and sends it out through the antenna 1201.

[1361] The method performed by the network side device in the foregoing embodiment can be implemented in the baseband device 1203, which comprises a baseband processor.

[1362] The baseband device 1203 may, for example, comprise at least one baseband board, and a plurality of chips are arranged on the baseband board, as shown in FIG. 12, one of which is a baseband processor, which is connected with the memory 1205 through a bus interface to call the programs in the memory 1205 and execute the network device operations shown in the foregoing method embodiments.

[1363] The network-side device can further include a network interface 1206, for example, a Common Public Radio Interface (CPRI).

[1364] Specifically, the network-side device 1200 of the embodiments of the present application further includes instructions or programs stored on the memory 1205 and executable on the processor 1204, the processor 1204 invokes the instructions or programs in the memory 1205 to perform the method performed by each module shown in FIG. 8 or FIG. 9, and achieves the same technical effects. To avoid repetition, the details are not described here.

[1365] The embodiments of the present application also provide a readable storage medium, the readable storage medium stores programs or instructions, the programs or instructions are executed by the processor to implement each process of the transmission method embodiments, and the same technical effects can be achieved. To avoid repetition, the details are not described here.

[1366] The processor is a processor in the terminal in the embodiments. The readable storage medium includes a computer readable storage medium, such as a computer readable memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. In some examples, the readable storage medium can be a non-transitory readable storage medium.

[1367] The embodiments of the present application further provide a chip, the chip includes a processor and a communication interface, the communication interface and the processor are coupled, the processor is used to run programs or instructions to implement each process of the transmission method embodiments, and the same technical effects can be achieved. To avoid repetition, the details are not described here.

[1368] It should be understood that the chip mentioned in the embodiments of the present application can also be referred to as a system chip, a system chip, a chip system or a system on chip, etc.

[1369] The embodiments of the present application further provide a computer program / program product, the computer program / program product is stored in a storage medium, the computer program / program product is executed by at least one processor to implement each process of the transmission method embodiments, and the same technical effects can be achieved. To avoid repetition, the details are not described here.

[1370] The embodiments of the present application further provide a wireless communication system, including: a first device and a second device, the first device can be used to execute the steps of the transmission method as above, and the second device can be used to execute the steps of the transmission method as above.

[1371] It should be noted that, in the present document, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a", "comprising", or "includes a", does not, without more constraints, preclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus of the present embodiments are not limited by the order of the steps or the order of the components, as described in the examples, unless otherwise specifically stated. For example, the steps of the described methods can be performed in any order, unless otherwise specifically stated. Also, features described in relation to certain examples can be combined in other examples.

[1372] From the above description of the embodiments, it is clear that the method of the embodiments can be realized by means of a computer software product, with the necessary universal hardware platform, of course, it can also be realized by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disc, optical disc, etc.), and includes a plurality of instructions for making the terminal or network side device execute the method of each embodiment of the present application.

[1373] The embodiments of the present application are described above in combination with the drawings, but the present application is not limited to the specific embodiments, and the specific embodiments are only illustrative, not restrictive. Those skilled in the art can make many forms of embodiments under the inspiration of the present application without departing from the scope of the present application and the protection scope of the claims, and these embodiments all belong to the protection scope of the present application.

Claims

1. A transmission method, comprising: obtaining, by a first device, first information, the first information being information obtained based on an artificial intelligence (AI) model; performing, by the first device, first transmission based on the first information, the first transmission corresponding to a half-duplex transmission mode or a full-duplex transmission mode; wherein the first information comprises at least one of the following: a first transmission mode, the first transmission mode comprising a half-duplex transmission mode or a full-duplex transmission mode; at least one spatial domain information; at least one first performance information, the first performance information being performance information related to transmission in a full-duplex transmission mode; at least one first transmission parameter, the first transmission parameter being a transmission parameter for uplink transmission; at least one second transmission parameter, the second transmission parameter being a transmission parameter for downlink transmission; at least one resource of a guard band; at least one related parameter of uplink transmit power; and at least one interference information.

2. The method of claim 1, wherein, The first information is obtained by the first device in the following manner: the first device receives the first information from a second device; or the first device obtains the first information based on the AI model. The spatial domain information comprises at least one of the following: spatial domain information corresponding to downlink transmission, and spatial domain information corresponding to uplink transmission.

3. The method of claim 1 or 2, wherein, The first performance information comprises at least one of the following:

4. The method of any one of claims 1 to 3, wherein, a probability of successful transmission in a full-duplex transmission mode; a probability of failed transmission in a full-duplex transmission mode; and a number of times of failed transmission in a full-duplex transmission mode. The first transmission parameter comprises at least one of the following: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, and a number of retransmissions.

5. The method of any one of claims 1 to 4, wherein, The second transmission parameter comprises at least one of the following: a time domain resource, a frequency domain resource, a spatial domain resource, a number of transmissions, and a number of retransmissions. The resource of the guard band comprises at least one of the following: a frequency domain location of the guard band, and a frequency domain size of the guard band. The related parameter of uplink transmit power comprises at least one of the following: a target uplink transmit power, a target receive power value, a maximum transmit power, a power boost value, and a power backoff value.

6. The method of any one of claims 1 to 5, wherein, The interference information comprises at least one of the following: interference strength information, and interference signal information.

7. The method of any one of claims 1 to 6, wherein, The interference strength information comprises at least one of the following: self-interference strength, mutual interference strength, and indication information indicating whether the interference strength satisfies a corresponding threshold.

8. The method of any one of claims 1 to 7, wherein, The interference signal information comprises at least one of the following: a reverse signal of at least one transmitted signal, and pre-processing information corresponding to at least one transmitted signal.

9. The method of claim 8, wherein, The first information further comprises at least one probability information; 10. The method of claim 8 or 9, wherein, wherein the probability information corresponds to at least one of the following: at least one spatial domain information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one resource of a guard band, and at least one related parameter of uplink transmit power.

11. The method of any one of claims 1 to 10, wherein, Input information of the AI model comprises at least one of the following: ​ 12. The method of any one of claims 1 to 11, wherein, ​ signal information, distance information, path loss information, second performance information, maximum transmit power of uplink transmission, area information, frequency domain information, beam information, time delay information, service related information, state information of the terminal, state information of the network side device, state information of the satellite, perception information, non-terrestrial network (NTN) base station information, channel information, and time information; the second performance information is performance information related to transmission in a full duplex transmission mode.

13. The method of claim 12, wherein, The signal information includes at least one of signal strength information, signal quality information, and interference signal strength information.

14. The method of claim 13, wherein, The signal strength information includes at least one of: reception strength information of an uplink signal between the first device and the second device; reception strength information of a downlink signal between the first device and the second device; or The signal quality information includes at least one of: signal quality information of an uplink signal between the first device and the second device; signal quality information of a downlink signal between the first device and the second device; or The interference signal strength information includes at least one of: self-interference strength information of the first device; mutual interference strength information of the first device; self-interference strength information of the second device; mutual interference strength information of the second device.

15. The method of any one of claims 12 to 14, wherein, The distance information includes at least one of: a distance between the first terminal and a network node of the first cell; a distance between a network node of the source cell and a network node of the target cell; a distance between a network node of the primary cell (Pcell) and a network node of the secondary cell (Scell); a distance between the first terminal and the second terminal; or The path loss information includes at least one of: a path loss between the first terminal and a network node of the first cell; a path loss between a network node of the source cell and a network node of the target cell; a path loss between a network node of the Pcell and a network node of the Scell; The first cell includes at least one of: the source cell, the target cell, the current camped cell or the current accessed cell, the Pcell, and the Scell; and the first terminal and the second terminal are both terminals of the first cell.

16. The method of any one of claims 12 to 15, wherein, The second performance information includes at least one of: a number of downlink signal reception failures of full duplex transmission in a specific time domain resource; a number of downlink signal reception failures of full duplex transmission in a specific frequency domain resource; a number of downlink signal reception failures of full duplex transmission in a specific spatial domain information; a number of downlink signal reception failures of full duplex transmission in a specific uplink transmit power; a number of downlink signal reception failures of full duplex transmission in a specific cell signal strength; a number of downlink signal reception failures of full duplex transmission in a specific interference signal strength; a number of downlink signal reception failures of full duplex transmission in a specific guard band resource.

17. The method of any one of claims 12 to 16, wherein, The area information includes at least one of the following: a transmission and reception point (TRP) identifier, a TRP group identifier, a cell identifier, a cell group identifier, a timing advance group (TAG) identifier, a tracking area (TA) identifier, and a radio access network notification area identifier.

18. The method of any one of claims 12 to 17, wherein, The service-related information includes at least one of the following: A load condition of at least one cell of the first cell; An interference condition of at least one cell of the first cell; A load condition corresponding to at least one spatial feature of the first cell; An interference condition corresponding to at least one spatial feature of the first cell; A load condition corresponding to at least one carrier or frequency point of the first cell; An interference condition corresponding to at least one carrier or frequency point of the first cell; The first cell includes at least one of the following: a source cell, a target cell, a currently camped cell or a currently accessed cell, a Pcell, and a Scell; and the spatial feature includes at least one of the following: an SSB, a TCI, a TRP, and a beam.

19. The method of any one of claims 12-18, wherein The state information of the terminal includes at least one of the following: location information of the terminal, distribution information of the terminal, a moving direction of the terminal, a moving speed of the terminal, an energy consumption condition of the terminal, a power condition of the terminal, operator information supported by the terminal, network type information supported by the terminal, panel orientation information of the terminal, a type of the terminal, network scenario information of the terminal, and environment information in which the terminal is located; Alternatively, The state information of the network-side device includes at least one of the following: transmission power information of the network-side device, location information of the network-side device, panel orientation information of the network-side device, an energy consumption condition of the network-side device, a power condition of the network-side device, and environment information in which the network-side device is located; Alternatively, The state information of the satellite includes at least one of the following: panel orientation information of the satellite, a moving speed of the satellite, and a moving direction of the satellite.

20. The method of any one of claims 1 to 19, wherein, The method further includes: The first device obtains first configuration information; The first configuration information includes at least one of the following: An AI model or an AI model identifier; An application range of AI model inference; A cycle of AI model inference; An effective duration of AI model inference; A trigger condition of AI model inference; Configuration parameters of the AI model, including at least one of the following: input information of the AI model, output information of the AI model, a type of the input information of the AI model, and a type of the output information of the AI model; First indication information indicating whether joint inference is supported or required.

21. The method of any one of claims 1 to 20, wherein, The method further includes: The first device obtains second indication information indicating activation information or deactivation information of the AI model; The first device activates or deactivates the AI model according to the second indication information.

22. The method of any one of claims 1 to 21, wherein, The trigger condition of using the AI model for inference includes at least one of the following: A timer timeout for triggering AI inference; Selection of full-duplex transmission configuration for transmission; A failure probability corresponding to full-duplex transmission is greater than or equal to a first threshold; The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to a second threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches a maximum transmission power; The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a third threshold; The terminal performs cell or TRP reselection; The terminal performs cell or TRP switching; Traffic arrives; Receiving indication information indicating to perform AI inference; The position of the terminal changes or the movement parameter of the terminal changes; The spatial information of the terminal changes or the transmission filter changes.

23. The method of any one of claims 1 to 22, wherein, The method further comprises: The first device trains at least part of the AI model; Or, The first device receives model information, and the model information is used to determine at least part of the AI model.

24. The method of claim 23, wherein, The conditions or events triggering the AI model training include at least one of the following: A timer for triggering AI model training expires; A TAG-related timer expires; Receiving indication information indicating AI training; The terminal accesses a new cell; The terminal switches a frequency point or a frequency band; The terminal switches an operator or a public land mobile network (PLMN); The AI model fails to infer; The AI model fails to infer continuously P times, P being a positive integer; The number of times of AI model inference failure reaches a fourth threshold; The AI model is used for inference; The terminal moves to a new cell or a tracking area or a geographic location; The movement speed of the terminal changes, or the change in the movement speed of the terminal is greater than or equal to a fifth threshold; The RSRP measurement value of the terminal changes, or the change in the RSRP measurement value of the terminal is greater than or equal to a sixth threshold; The duration of the timer for AI model training expires; K times of model supervision occur or S consecutive times of model supervision occur, K and S being positive integers; The external environment of the terminal changes; The movement speed of the terminal is greater than or equal to a seventh threshold, or the acceleration of the terminal is greater than or equal to an eighth threshold; The position of the terminal changes, or the change in the position of the terminal is greater than or equal to a ninth threshold; The movement parameter of the terminal changes; The spatial information of the terminal changes or the spatial transmission filter of the terminal changes; The network-side device configures a full-duplex transmission configuration; The failure probability corresponding to the full-duplex transmission is greater than or equal to a tenth threshold; The uplink transmission power corresponding to the full-duplex transmission is greater than or equal to an eleventh threshold, or the uplink transmission power corresponding to the full-duplex transmission reaches a maximum transmission power; The interference signal strength corresponding to the full-duplex transmission is greater than or equal to a twelfth threshold; The terminal performs cell or TRP switching; The terminal performs cell or TRP reselection; Traffic arrives; Receiving indication information indicating to determine full-duplex transmission information based on the AI model.

25. The method of claim 23 or 24, wherein, The labels for the AI model training include at least one of the following: Obtaining or not obtaining first information satisfying a performance requirement; The number of obtained first information; The duration of AI model training; The energy consumption of AI model training; First information required for transmission between the terminal and a network node of the first cell.

26. The method of any one of claims 1 to 25, wherein, The method further comprises: The first device supervises the AI model; Or, The first device receives a model supervision result of the AI model.

27. The method of claim 26, wherein, The configuration information for the AI model supervision includes at least one of the following: An AI model or an AI model identifier that needs to be supervised; A period of model supervision; A duration of model supervision; Detection window related information of model supervision; Trigger conditions of model supervision; Indicators of model supervision; Labels of model supervision.

28. The method of claim 26 or 27, wherein, The trigger conditions of the AI model supervision include at least one of the following: The result of the AI model inference does not meet the accuracy requirement; At least one indicator of the AI model inference does not meet the requirement; The indicators of model supervision do not meet the requirement; The timer for the AI model supervision is timed out; The terminal switches a cell or a TRP or a beam; The AI model inference fails; The AI model continuously fails T times of inference, where T is a positive integer; The number of times of AI model inference failure reaches a third preset number; The AI model is used for inference; The terminal moves to a new cell or a tracking area or a geographical location; The moving speed of the terminal is greater than or equal to a thirteenth threshold, or the acceleration of the terminal is greater than or equal to a fourteenth threshold; The external environment of the inference device of the AI model changes.

29. The method of any one of claims 1 to 28, wherein, The method further includes at least one of the following: The first device sends AI related capability information of the first device; The first device determines AI related capability information of a second device; The AI related capability information is used to indicate at least one of the following: Possessing or not possessing the capability of training an AI model for obtaining first information; Possessing or not possessing the capability of obtaining first information through an AI model; Possessing or not possessing the capability of sending first auxiliary information, the first auxiliary information being used to obtain first information through an AI model; Possessing or not possessing the capability of sending second auxiliary information, the second auxiliary information being used to train an AI model for obtaining first information.

30. A transmission method, comprising: A second device performs a second operation, the second operation including at least one of the following: Obtaining first information based on an AI model and sending the first information to a first device; Receiving second information from the first device, the second information including at least one of the following: the first information, at least part of the input information of the AI model; Training at least part of the AI model; Sending model information, the model information being used to determine at least part of the AI model; Sending a supervision result of the AI model; Sending indication information for triggering AI model training; Sending indication information for triggering AI model inference; The AI model is used to predict at least one of the following: A first transmission mode, the first transmission mode including a half duplex transmission mode or a full duplex transmission mode; At least one space domain information; At least one first performance information, the first performance information being performance information related to transmission in a full duplex transmission mode; At least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission; At least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission; At least one resource of a guard band; At least one related parameter of uplink transmission power; At least one interference information.

31. The method of claim 30, wherein, The first information further includes at least one probability information. The probability information corresponds to at least one of the following: at least one spatial domain information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one resource of a guard band, at least one related parameter of an uplink transmission power.

32. The method of claim 30 or 31, wherein, The input information of the AI model includes at least one of the following: signal information, distance information, path loss information, second performance information, maximum transmission power of uplink transmission, area information, frequency domain information, beam information, time delay information, service related information, state information of a terminal, state information of a network side device, state information of a satellite, perception information, non-terrestrial network (NTN) base station information, channel information, and time information; the second performance information is performance information related to transmission in a full duplex transmission mode.

33. A transmission apparatus, comprising: a processing module configured to obtain first information, the first information being information obtained based on an artificial intelligence (AI) model; a transceiver configured to perform first transmission based on the first information, the transmission mode corresponding to the first transmission being a half duplex transmission mode or a full duplex transmission mode; wherein the first information includes at least one of the following: a first transmission mode, the first transmission mode including a half duplex transmission mode or a full duplex transmission mode; at least one spatial domain information; at least one first performance information, the first performance information being performance information related to transmission in a full duplex transmission mode; at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission; at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission; at least one resource of a guard band; at least one related parameter of an uplink transmission power; at least one interference information.

34. A transmission apparatus, comprising: a processing module configured to perform a second operation, the second operation including at least one of the following: obtaining first information based on an AI model and sending the first information to a first device; receiving second information from a first device, the second information including at least one of the following: the first information, at least part of input information of the AI model; training at least part of the AI model; sending model information, the model information being used to determine at least part of the AI model; sending a supervision result of the AI model; sending indication information for triggering training of the AI model; sending indication information for triggering inference of the AI model; wherein the AI model is used to predict at least one of the following: a first transmission mode, the first transmission mode including a half duplex transmission mode or a full duplex transmission mode; at least one spatial domain information; at least one first performance information, the first performance information being performance information related to transmission in a full duplex transmission mode; at least one first transmission parameter, the first transmission parameter being a transmission parameter of uplink transmission; at least one second transmission parameter, the second transmission parameter being a transmission parameter of downlink transmission; at least one resource of a guard band; at least one related parameter of an uplink transmission power; at least one interference information.

35. A first device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implement the steps of the transmission method of any one of claims 1 to 29.

36. A second device comprising a processor and a memory, the memory storing programs or instructions executable on the processor, the programs or instructions, when executed by the processor, implement the steps of the transmission method of any one of claims 30 to 32.

37. A readable storage medium, the readable storage medium storing programs or instructions, the programs or instructions, when executed by a processor, implement the steps of the transmission method of any one of claims 1 to 29, or implement the steps of the transmission method of any one of claims 30 to 32.

38. A computer program product, the computer program product being executed by at least one processor to implement the steps of the transmission method of any one of claims 1 to 29, or implement the steps of the transmission method of any one of claims 30 to 32.

Images