Transmission method and device, first equipment and second equipment

Abstract

The invention discloses a transmission method and device, first equipment and second equipment, and belongs to the technical field of communication, and the transmission method comprises the steps that the first equipment obtains first information, and the first information is information obtained based on an AI model; 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; wherein the first information comprises at least one of the following items: a first transmission mode; at least one piece of airspace information; at least one piece of first performance information, wherein the first performance information is performance information related to transmission in a full duplex transmission mode; at least one first transmission parameter, wherein the first transmission parameter is a transmission parameter of uplink transmission; at least one second transmission parameter, wherein the second transmission parameter is a transmission parameter of downlink transmission; resources of at least one guard band; at least one related parameter of uplink transmission power; and at least one piece of interference information.

Description

Technical Field

[0001] This application belongs to the field of communication technology, and specifically relates to a transmission method, apparatus, first device and second device. Background Technology

[0002] To improve the latency and coverage performance of Time Division Duplexing (TDD) systems, full-duplex transmission has been introduced, allowing network-side devices or terminals to transmit in full-duplex mode. However, when network-side devices or terminals use full-duplex transmission, the received signal is subject to interference from the transmitted signal. Existing interference suppression and transmission methods often lead to low resource utilization and performance degradation. Therefore, it is evident that introducing full-duplex transmission in related technologies can easily result in a decrease in transmission performance. Summary of the Invention

[0003] This application provides a transmission method, apparatus, first device, and second device that can determine the transmission mode or transmission-related parameters based on an AI model when full-duplex transmission is introduced, which helps to ensure transmission performance.

[0004] Firstly, a transmission method is provided, the method comprising:

[0005] The first device acquires first information, which is information obtained based on an artificial intelligence (AI) model;

[0006] The first device performs a first transmission based on the first information, and the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode.

[0007] The first information includes at least one of the following:

[0008] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0009] At least one piece of spatial information;

[0010] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0011] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0012] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0013] Resources for at least one protective belt;

[0014] At least one parameter related to uplink transmit power;

[0015] At least one piece of interference information.

[0016] Secondly, a transmission device is provided, the device comprising:

[0017] The processing module is used to acquire first information, which is information obtained based on an artificial intelligence (AI) model.

[0018] The transceiver module is used to perform a first transmission based on the first information, wherein the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode.

[0019] The first information includes at least one of the following:

[0020] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0021] At least one piece of spatial information;

[0022] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0023] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0024] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0025] Resources for at least one protective belt;

[0026] At least one parameter related to uplink transmit power;

[0027] At least one piece of interference information.

[0028] Thirdly, a transmission method is provided, the method comprising:

[0029] The second device performs a second operation, the second operation including at least one of the following:

[0030] The first information is obtained based on the AI ​​model, and the first information is sent to the first device;

[0031] Receive second information from the first device, the second information including at least one of the following: first information, at least a portion of the input information of the AI ​​model;

[0032] Training at least a portion of the AI ​​model;

[0033] Send model information, which is used to identify at least a portion of the AI ​​model;

[0034] Send the supervision results of the AI ​​model;

[0035] Send an instruction message to trigger AI model training;

[0036] Send an instruction message to trigger AI model inference;

[0037] The AI ​​model is used to predict at least one of the following:

[0038] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0039] At least one piece of spatial information;

[0040] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0041] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0042] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0043] Resources for at least one protective belt;

[0044] At least one parameter related to uplink transmit power;

[0045] At least one piece of interference information.

[0046] Fourthly, a transmission device is provided, the device comprising:

[0047] A processing module is configured to perform a second operation, the second operation including at least one of the following:

[0048] The first information is obtained based on the AI ​​model, and the first information is sent to the first device;

[0049] Receive second information from the first device, the second information including at least one of the following: first information, at least a portion of the input information of the AI ​​model;

[0050] Training at least a portion of the AI ​​model;

[0051] Send model information, which is used to identify at least a portion of the AI ​​model;

[0052] Send the supervision results of the AI ​​model;

[0053] Send an instruction message to trigger AI model training;

[0054] Send an instruction message to trigger AI model inference;

[0055] The AI ​​model is used to predict at least one of the following:

[0056] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0057] At least one piece of spatial information;

[0058] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0059] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0060] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0061] Resources for at least one protective belt;

[0062] At least one parameter related to uplink transmit power;

[0063] At least one piece of interference information.

[0064] Fifthly, a transmission apparatus is provided, the apparatus being configured to perform the steps of the method described in the first aspect, or to implement the steps of the method described in the third aspect.

[0065] In a sixth aspect, a first device is provided, the first device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the first aspect.

[0066] In a seventh aspect, a first device is provided, including a processor and a communication interface, wherein the processor is used to acquire first information, the first information being information obtained based on an artificial intelligence (AI) model; the communication interface is used to perform a 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.

[0067] The first information includes at least one of the following:

[0068] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0069] At least one piece of spatial information;

[0070] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0071] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0072] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0073] Resources for at least one protective belt;

[0074] At least one parameter related to uplink transmit power;

[0075] At least one piece of interference information.

[0076] In an eighth aspect, a second device is provided, the second device including a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the method as described in the third aspect.

[0077] A ninth aspect provides a second device, 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:

[0078] The first information is obtained based on the AI ​​model, and the first information is sent to the first device;

[0079] Receive second information from the first device, the second information including at least one of the following: first information, at least a portion of the input information of the AI ​​model;

[0080] Training at least a portion of the AI ​​model;

[0081] Send model information, which is used to identify at least a portion of the AI ​​model;

[0082] Send the supervision results of the AI ​​model;

[0083] Send an instruction message to trigger AI model training;

[0084] Send an instruction message to trigger AI model inference;

[0085] The AI ​​model is used to predict at least one of the following:

[0086] A first transmission mode, the first transmission mode including a half-duplex transmission mode or a full-duplex transmission mode;

[0087] At least one piece of spatial information;

[0088] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0089] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission;

[0090] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0091] Resources for at least one protective belt;

[0092] At least one parameter related to uplink transmit power;

[0093] At least one piece of interference information.

[0094] In a tenth aspect, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method described in the first aspect, or implement the steps of the method described in the third aspect.

[0095] Eleventhly, a wireless communication system is provided, comprising: a first device and a second device, wherein the first device is configured to perform the steps of the transmission method as described in the first aspect, and the second device is configured to perform the steps of the transmission method as described in the third aspect.

[0096] In a twelfth aspect, a chip is provided, the chip including a processor and a communication interface coupled to the processor, the processor being configured to run a program or instructions to implement the steps of the method described in the first aspect, or to implement the steps of the method described in the third aspect.

[0097] In a thirteenth aspect, a computer program / program product is provided, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method as described in the first aspect, or to implement the steps of the method as described in the third aspect.

[0098] In this embodiment, a first device acquires first information, which is information obtained based on an AI model; and performs a first transmission based on the first information, wherein the transmission mode corresponding to the first transmission is 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, which includes a half-duplex transmission mode or a full-duplex transmission mode; at least one spatial information; at least one first performance information, which is performance information related to transmission in full-duplex transmission mode; at least one first transmission parameter, which is an uplink transmission parameter; at least one second transmission parameter, which is a downlink transmission parameter; at least one guard band resource; at least one uplink transmit power related parameter; and at least one interference information. That is, in this embodiment, the transmission mode or transmission-related parameters are obtained based on an AI model for transmission, which helps to ensure transmission performance. Attached Figure Description

[0099] Figure 1 This is a block diagram of a wireless communication system applicable to embodiments of this application;

[0100] Figure 2a This is a schematic diagram of the neural network provided in an embodiment of this application;

[0101] Figure 2b This is a schematic diagram of a neuron provided in an embodiment of this application;

[0102] Figure 3 This is a schematic diagram of the AI ​​lifecycle management framework provided in the embodiments of this application;

[0103] Figures 4a to 4d This is a schematic diagram of full-duplex transmission provided in an embodiment of this application;

[0104] Figure 5 This is a flowchart of Rel-15 NR Uu CSI acquisition provided in the embodiments of this application;

[0105] Figure 6 This is a flowchart of a transmission method provided in an embodiment of this application;

[0106] Figure 7 This is a flowchart of another transmission method provided in an embodiment of this application;

[0107] Figure 8 This is a structural diagram of a transmission device provided in an embodiment of this application;

[0108] Figure 9 This is a structural diagram of another transmission device provided in an embodiment of this application;

[0109] Figure 10This is a structural diagram of the communication device provided in the embodiments of this application;

[0110] Figure 11 This is a structural diagram of the terminal provided in the embodiments of this application;

[0111] Figure 12 This is a structural diagram of the network-side device provided in the embodiments of this application. Detailed Implementation

[0112] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0113] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such terms can be used interchangeably where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first" and "second" are generally of the same class, not limited in number; for example, the first object can be one or more. Furthermore, "or" in this application indicates at least one of the connected objects. For example, the scope of protection for "A or B" covers at least three scenarios: Scenario 1: including A but not B; Scenario 2: including B but not A; Scenario 3: including both A and B. In addition, the terms "A and / or B," "at least one of A and B," and "at least one of A or B" also cover at least the above three scenarios. The character " / " generally indicates that the preceding and following objects are in an "or" relationship.

[0114] The term "instruction" in this application can be either a direct instruction (or explicit instruction) or an indirect instruction (or implicit instruction). A direct instruction can be understood as one in which the sender explicitly informs the receiver of specific information, the operation to be performed, or the requested result, etc., in the instruction sent. An indirect instruction can be understood as one in which the receiver determines the corresponding information based on the instruction sent by the sender, or makes a judgment and determines the operation to be performed or the requested result, etc., based on the judgment result.

[0115] It is worth noting that the technologies described in this application are not limited to Long Term Evolution (LTE) / LTE-Advanced (LTE-A) systems, but can also be used in other wireless communication systems, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), Frequency Division Multiple Access (FDMA), Orthogonal Frequency Division Multiple Access (OFDMA), Single-carrier Frequency-Division Multiple Access (SC-FDMA), or other systems. The terms "system" and "network" in this application are often used interchangeably, and the described technologies can be used with the systems and radio technologies mentioned above, as well as with other systems and radio technologies. The following description describes New Radio (NR) systems for illustrative purposes, and the term NR is used in most of the following description; however, these technologies can also be applied to systems other than NR systems, such as 6th generation (6G) radio systems. th Generation 6G communication system.

[0116] Figure 1This diagram illustrates a block diagram of a wireless communication system applicable to embodiments of this application. The wireless communication system includes a terminal 11 and a network-side device 12. The terminal 11 can be a mobile phone, tablet computer, laptop computer, notebook computer, personal digital assistant (PDA), handheld computer, netbook, ultra-mobile personal computer (UMPC), mobile internet device (MID), augmented reality (AR), virtual reality (VR) device, robot, wearable device, flight vehicle, vehicle user equipment (VUE), shipboard equipment, pedestrian user equipment (PUE), smart home devices (home appliances with wireless communication capabilities, such as refrigerators, televisions, washing machines, or furniture), game consoles, personal computers (PCs), ATMs, or self-service machines, etc. Wearable devices include: smartwatches, smart bracelets, smart headphones, smart glasses, smart jewelry (smart bracelets, smart chains, smart rings, smart necklaces, smart anklets, smart anklets, etc.), smart wristbands, smart clothing, etc. Among these, in-vehicle devices can also be referred to as in-vehicle terminals, in-vehicle controllers, in-vehicle modules, in-vehicle components, in-vehicle chips, or in-vehicle units, etc. It should be noted that the specific type of terminal 11 is not limited in this application embodiment. Network-side equipment 12 may include access network equipment or core network equipment, wherein access network equipment may also be referred to as Radio Access Network (RAN) equipment, radio access network function, or radio access network unit. Access network equipment may include base stations, Wireless Local Area Network (WLAN) access points (AS), or Wireless Fidelity (WiFi) nodes, etc.In this context, a base station may be referred to as a Node B (NB), Evolved Node B (eNB), Next Generation Node B (gNB), New Radio Node B (NR Node B), Access Point, Relay Base Station (RBS), Serving Base Station (SBS), Base Transceiver Station (BTS), Radio Base Station, Radio Transceiver, Basic Service Set (BSS), Extended Service Set (ESS), Home Node B (HNB), Home Evolved Node B, Transmit / Receive Point (TRP), or any other suitable term in the relevant field. As long as the same technical effect is achieved, the base station is not limited to any specific technical term. It should be noted that in this application embodiment, only a base station in an NR system is used as an example for introduction, and the specific type of base station is not limited.

[0117] Core network equipment, also known as core network nodes, core network functions, or core network elements, includes, but is not limited to, at least one of the following: Mobility Management Entity (MME), Access and Mobility Management Function (AMF), Session Management Function (SMF), User Plane Function (UPF), Policy Control Function (PCF), Policy and Charging Rules Function (PCRF), Edge Application Server Discovery Function (EASDF), Unified Data Management (UDM), Unified Data Repository (UDR), Home Subscriber Server (HSS), Centralized network configuration (CNC), Network Repository Function (NRF), Network Exposure Function (NEF), Local NEF (or L-NEF), and Binding Support Function. Support Functions (BSF), Application Functions (AF), Location Management Functions (LMF), Gateway Mobile Location Centres (GMLC), and Network Data Analytics Functions (NWDAF), etc. It should be noted that this application embodiment only uses core network equipment in the NR system as an example and does not limit the specific type of core network equipment. If the name of the core network equipment mentioned in this application embodiment changes in subsequent protocol versions (e.g., 6G), it will still be within the scope of protection of this application.

[0118] Optionally, the core network equipment can be implemented by one or more functional modules in a single device, or by multiple devices working together; this application does not specifically limit this. It is understood that a functional module can be a network element in a hardware device, a software functional module running on dedicated hardware, or a virtualized functional module instantiated on a platform (e.g., a cloud platform).

[0119] For ease of understanding, the following describes some aspects of the embodiments of this application:

[0120] I. Artificial Intelligence (AI) / Machine Learning (ML)

[0121] Artificial intelligence (AI) has been widely applied in various fields. Integrating AI into wireless communication networks to significantly improve technical indicators such as throughput, latency, and user capacity is an important task for future wireless communication networks. AI modules can be implemented in various ways, such as neural networks, decision trees, support vector machines, and Bayesian classifiers. This application uses neural networks as an example for illustration, but it does not limit the specific type of AI module.

[0122] For example, a neural network can be as follows Figure 2a As shown, a neural network is composed of neurons, and each neuron can... Figure 2b As shown in the diagram. Here, a1, a2, ..., aK are the inputs, w is the weight (multiplicative coefficient), b is the bias (additive coefficient), and σ(.) is the activation function. Common activation functions include Sigmoid, tanh, and the Rectified Linear Unit (ReLU), etc.

[0123] The parameters of a neural network are optimized using gradient optimization algorithms. Gradient optimization algorithms are a class of algorithms that minimize or maximize an objective function (also known as a loss function), which is often a mathematical combination of model parameters and data. For example, given data X and its corresponding label Y, we construct a neural network model f(.). With the model, we can obtain the predicted output f(x) based on the input x, and calculate the difference between the predicted value and the true value (f(x) - Y), which is the loss function. The goal is to find suitable W and b to minimize the value of the loss function, where a smaller loss value indicates that the model is closer to the reality.

[0124] Most common optimization algorithms are based on the error back propagation (BP) algorithm. The basic idea of ​​the BP algorithm is that the learning process consists of two parts: forward propagation of the signal and backward propagation of the error. During forward propagation, the input sample is introduced from the input layer, processed layer by layer by the hidden layers, and then propagated to the output layer. If the actual output of the output layer does not match the expected output, the process transitions to the error back propagation stage. Error back propagation involves propagating the output error back to the input layer layer by layer through the hidden layers, distributing the error to all units in each layer, thus obtaining the error signal of each unit. This error signal serves as the basis for adjusting the weights of each unit. This process of adjusting the weights through forward and backward propagation is repeated continuously. This continuous adjustment of weights is the learning and training process of the network. This process continues until the error of the network output is reduced to an acceptable level, or until the predetermined number of learning iterations is reached.

[0125] Common optimization algorithms include gradient descent, stochastic gradient descent (SGD), mini-batch gradient descent, momentum method, Nesterov (named after the inventor, specifically stochastic gradient descent with momentum), adaptive gradient descent (Adagrad), Adadelta, root mean square propagation (RMSprop), and adaptive momentum estimation (Adam).

[0126] During error backpropagation, these optimization algorithms calculate the gradient based on the error / loss obtained from the loss function with respect to the current neuron, add the learning rate, previous gradients / derivatives / partial derivatives, etc., and then pass the gradient to the previous layer.

[0127] Generally, the AI ​​algorithms and models selected vary depending on the type of problem being solved. The main method for improving 5G network performance using AI is to enhance or replace existing algorithms or processing modules with neural network-based algorithms and AI models. In specific scenarios, neural network-based algorithms and AI models can achieve better performance than deterministic algorithms. Commonly used neural networks include deep neural networks, convolutional neural networks, and recurrent neural networks. Existing AI tools can be used to build, train, and validate neural networks.

[0128] II. Fine-tuning

[0129] In practice, due to the insufficient size of real-time acquired datasets, directly training a neural network often fails to achieve convergence. A common approach is to pre-train the network using a large amount of offline collected data until it converges. Then, the parameters of the pre-trained neural network are fine-tuned using real-time acquired data to adapt the network to the real-world environment. Fine-tuning can be considered a training process that uses the parameters of the pre-trained neural network as initialization. During the fine-tuning phase, the parameters of some layers can be frozen; generally, layers closer to the input are frozen, while layers closer to the output are activated. This ensures that the network can still converge. The smaller the amount of data during the fine-tuning phase, the more layers should be frozen, with only a small number of layers near the output being fine-tuned.

[0130] III. Generalization of Neural Networks

[0131] Generalization refers to the ability of a neural network to produce reasonable outputs on data not encountered during its training or learning process. To address the generalization problem caused by the variable wireless transmission environment, neural network-based wireless communication systems offer two solutions. The first is to train different neural networks under different transmission conditions, obtaining multiple sets of network parameters, and then switching these parameters as the actual environment changes. The second is to train a common neural network based on mixed data, where the network parameters do not change with the environment. Each approach has its advantages and disadvantages: the first approach performs excellently under different transmission conditions, but requires storing multiple network parameters and switching them as needed, which incurs signaling overhead and frequent switching issues; the second approach only requires storing one set of neural network parameters without switching, but it cannot achieve optimal performance under every transmission condition. The construction method of the mixed dataset affects the performance of the second approach.

[0132] IV. Labels

[0133] In machine learning and deep learning, labels typically refer to the identifiers or annotations of the true category or target value of a data sample. Labels are used to represent the information that the model should learn and predict. The following examples illustrate this:

[0134] Labels in classification tasks: In classification tasks, labels indicate which category a data sample belongs to. For example, in image classification, each image sample has a label that indicates the category of the object or scene contained in the image, such as "dog" or "cat".

[0135] Labels in object detection: In object detection tasks, labels typically include the object's location information (e.g., the object's bounding box) and category information. Each label identifies a target object in an image, including its location and category. Labels in regression tasks:

[0136] In regression tasks, labels typically represent the continuous or real-valued objective to be predicted. For example, in a house price prediction task, the label could be the actual selling price of a house.

[0137] Labels in sequence labeling: In natural language processing, labels in sequence labeling tasks are often used for tasks such as part-of-speech tagging and named entity recognition. Labels are used to represent the attributes or categories of each word or character in a text sequence.

[0138] Labels are a crucial component in supervised learning tasks, used to train machine learning models. Models learn patterns and regularities by comparing themselves to true labels in order to make predictions or classifications on unseen data. The quality and accuracy of the labels are critical to the model's performance.

[0139] V. AI Lifecycle Management (LCM)

[0140] AI / ML model lifecycle management includes multiple AI functional modules: model training, model deployment, model inference, model monitoring, and model updates. For example, a specific framework for AI lifecycle management can be as follows: Figure 3 As shown.

[0141] (1) Model training

[0142] This function performs AI model training, validation, and testing, generating model performance metrics that can be used as part of the model testing process. If needed, it also handles data preparation based on the training data provided by the data collection function, such as data preprocessing and cleaning, formatting, and transformation.

[0143] Training / Update Model: If a model storage function is available, it is used to transfer trained, validated, and tested AI models to the model storage function, or to transfer updated versions of the model to the model storage function.

[0144] (2) Model Management

[0145] This module monitors the operation of AI models or the deployment of AI functions, such as model selection / activation / deactivation / switching / rollback, and provides feedback on model monitoring performance. It is also responsible for making decisions based on data received from the data collection and inference modules to ensure correct inference operations.

[0146] Management instructions: Information used by the model management function to input to the model inference function. This information may include selecting / deactivating / activating / switching models or reverting to non-AI / ML operations (i.e., operations independent of the inference process) using AI models or AI / ML-based functions.

[0147] Model transfer request: Used to request a model from the model storage function.

[0148] Performance Feedback / Retraining Request: Information required for model training functions to input, such as for model (re)training or updating purposes.

[0149] (3) Model reasoning

[0150] The data (i.e., inference data) provided by the data collection function is used as input to provide the output of the applied AI model. If necessary, the inference function is also responsible for data preparation based on the inference data provided by the data collection function (e.g., data preprocessing and cleaning, formatting and transformation).

[0151] Inference output: Data used by management functions to monitor the performance of AI models or AI / ML functions.

[0152] VI. Full Duplex Mode

[0153] In 5G mobile communication systems, full duplexes have been enhanced to adapt to diverse scenarios and service requirements. Key 5G scenarios include Enhanced Mobile Broadband (eMBB), Ultra-Reliable and Low Latency Communications (URLLC), and Massive Machine Type Communication (mMTC). These scenarios place demands on the system to achieve high reliability, low latency, high bandwidth, and wide coverage.

[0154] In NR, configuring full-duplex operation can significantly improve the latency and coverage performance of time division multiplexing (TDD) systems.

[0155] Subbands non-overlapping full duplex can improve transmission latency and enhance coverage.

[0156] For a downlink (DL) slot (configured by tdd-UL-DL-ConfigurationCommon or tdd-UL-DL-ConfigurationDedicated), the network configures the DL bandwidth part (BWP) for the UE. For an uplink (UL) slot, the network configures the UL BWP for the UE. For example, slots 1 and 4.

[0157] See Figure 4a For full duplex scenarios, the following cases exist:

[0158] Scenario 1: Configure DL BWP, i.e., slot 1;

[0159] Scenario 2: Configure DL BWP and UL sub-band, i.e., slot 2.

[0160] See Figure 4b For a UL slot (configured by tdd-UL-DL-ConfigurationCommon or tdd-UL-DL-ConfigurationDedicated), the following situations exist:

[0161] Scenario 3: Configure UL BWP, i.e., slot 4;

[0162] Case 4: Configure UL BWP and DL subband, i.e., slot 5.

[0163] For Seamless Bidirectional Forwarding Detection (SBFD) operation, an SBFD subband consists of a single resource block (RB) or a continuous set of RBs with the same transmission direction.

[0164] The time unit (e.g., slot or symbol) used by gNB for SBFD operations can be referred to as the SBFD time unit (e.g., slot or symbol).

[0165] See Figure 4c For Rel-15, the base station and UE can only transmit or receive at any given time. For Rel-18, the gNB is full-duplex, allowing simultaneous transmission and reception, while the UE can only use half-duplex mode, meaning it can only transmit or receive at any given time. For UE-side full-duplex, both the gNB and UE can transmit and receive simultaneously.

[0166] For full-duplex operation on the UE side, a larger guard band (GB) (greater than the base station frequency division (FD) in GB) may be required to suppress self-interference. See [link to relevant documentation] Figure 4d .

[0167] For a communication device, simultaneous UL reception and DL transmission can cause self-interference. To ensure transmission in the direction of interference, the communication device needs to have self-interference cancellation capabilities, such as reserving a guard band between the receive and transmit bands. However, this will reduce the throughput of the UE.

[0168] It should also be noted that related technologies typically employ interference isolation or cancellation measures to suppress interference. For example, interference isolation can be achieved by increasing the number of antennas for antenna isolation, or by increasing the frequency domain guard band for frequency domain isolation. Interference cancellation requires estimating or reproducing the interference signal, which may introduce additional components and is susceptible to environmental and temperature influences, leading to inaccurate interference signal estimation. Interference isolation requires reserving significant resources for the frequency domain guard band, potentially resulting in lower resource utilization. Furthermore, to ensure reception performance, it may be necessary to reduce transmit power, which could degrade transmission performance.

[0169] In 5G and future 6G systems, both base stations and terminals are likely to adopt full-duplex mode.

[0170] VII. Regarding Quasi-Co-Location (QCL)

[0171] In the embodiments of this application, the descriptions of quasi-co-addressing of the Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), and Synchronous Signal Block (SSB) / Channel State Information Reference Signal (CSI-RS) are the same as the descriptions of quasi-co-addressing of the Demodulation Reference Signal (DMRS) or DMRS antenna ports with SSB / CSI-RS; or it can be understood that the quasi-co-addressing attributes of the two are the same.

[0172] The Transmission Configuration Indication (TCI) state indicates that the network indicates that the downlink channel PDCCH, PDSCH, or the DMRS antenna port of PDCCH, PDSCH is quasi-co-located with a certain downlink reference signal (RS) (e.g., SSB / CSI-RS).

[0173] Quasi-co-located properties include at least one of the following: Doppler shift, Doppler spread, average delay, delay spread, and spatial RX parameters.

[0174] VIII. Regarding Multiple Antennas

[0175] Radio access technology standards such as Long Term Evolution (LTE) and LTE-Advanced (LTE-A) are built upon Multiple-Input Multiple-Output (MIMO) and Orthogonal Frequency Division Multiplexing (OFDM) technologies. MIMO technology utilizes the spatial degrees of freedom available in multi-antenna systems to improve peak data rates and system spectral efficiency.

[0176] During the standardization process, the dimensions of MIMO technology have been continuously expanded. In LTE Release 8 (Rel-8), up to four layers of MIMO transmission can be supported. In Release 9 (Rel-9), Multi-User MIMO (MU-MIMO) technology was enhanced, and up to four downlink data layers can be supported in MU-MIMO transmission in Transmission Mode (TM)-8. In Release 10 (Rel-10), the transmission capability of Single-User MIMO (SU-MIMO) was expanded to a maximum of eight data layers.

[0177] The industry is further advancing MIMO technology towards three-dimensional and large-scale implementation. Currently, 3GPP has completed its research project on three-dimensional (3D) channel modeling and is conducting research and standardization work on Enhanced Full Dimension MIMO (eFD-MIMO) and NR MIMO. It is foreseeable that larger-scale MIMO technology with more antenna ports will be introduced into future 5G mobile communication systems.

[0178] Massive MIMO technology uses massive antenna arrays, which can greatly improve the system's bandwidth utilization efficiency and support a larger number of access users. Therefore, major research organizations regard massive MIMO technology as one of the most promising physical layer technologies in next-generation mobile communication systems.

[0179] In massive MIMO technology, using an all-digital array can achieve maximum spatial resolution and optimal MU-MIMO performance. However, this structure requires a large number of analog-to-digital (AD) / digital-to-analog (DA) conversion devices and a large number of complete RF-baseband processing channels, which will be a huge burden in terms of both equipment cost and baseband processing complexity.

[0180] To mitigate cost and equipment complexity, hybrid analog-digital beamforming technology has emerged. This involves adding a beamforming stage to the radio frequency signal near the antenna system front-end, building upon traditional digital beamforming. Analog beamforming provides a relatively simple, coarse match between the transmitted signal and the channel. The equivalent channel dimension formed after analog beamforming is smaller than the actual number of antennas, significantly reducing the required AD / DA converters, digital channels, and baseband processing complexity. Residual interference from the analog beamforming stage can be further processed in the digital domain, ensuring the quality of MU-MIMO transmission. Compared to all-digital beamforming, hybrid analog-digital beamforming represents a trade-off between performance and complexity, showing high practical potential in high-frequency, high-bandwidth systems or systems with a large number of antennas.

[0181] IX. Regarding high-frequency bands

[0182] Research on next-generation communication systems beyond 4G aims to increase the supported operating frequency bands to above 6GHz, with a maximum of approximately 100GHz. High-frequency bands have relatively abundant idle frequency resources, providing greater throughput for data transmission. Currently, 3GPP has completed high-frequency channel modeling. High-frequency signals have shorter wavelengths, allowing for the placement of more antenna elements on the same panel size compared to low-frequency bands, and enabling the formation of more directional beams with narrower lobes using beamforming technology. Therefore, combining massive MIMO with high-frequency communication is also a future trend.

[0183] 10. Regarding beam measurement and beam reporting

[0184] Analog beamforming is transmitted across the full bandwidth, and each polarization element on the panel of each high-frequency antenna array can only transmit an analog beam in a time-division multiplexed manner. The beamforming weights of the analog beam are achieved by adjusting the parameters of devices such as the RF front-end phase shifter.

[0185] Currently, in academia and industry, a polling method is commonly used to train simulated beamforming vectors. This involves each element on each antenna panel, in each polarization direction, sequentially transmitting training signals (i.e., candidate beamforming vectors) at predetermined times using time-division multiplexing. The terminal then measures and sends back a beam report, which the network uses to implement simulated beam transmission in the next transmission. The beam report typically includes the identifiers of several optimal transmit beams and the measured received power of each transmit beam.

[0186] When performing beam measurements, the network configures beam reporting information, which is associated with a Reference Signal Resource (RS) setting. This RS resource setting contains at least one RS resource set, and each RS resource set includes at least one reference signal resource, such as an SSB resource or a 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) for each RS resource and reports at least one optimal measurement result to the network. The reported information includes the SSB Rank Indicator (RI) or Channel State Information Reference Signal Resource Indicator (CRI), and L1-RSRP / L1-SINR.

[0187] The beam report configuration information specifies whether the report is a group-based beam report. If it's a non-group-based beam report, the UE reports at least one optimal beam and its quality, allowing the network to determine the beam used to transmit channels or signals to the UE. If it's a group-based beam report, the UE reports a pair of beams and their quality; when the network uses this pair of beams to transmit information to the UE, the UE can receive them simultaneously.

[0188] 11. Beam Alignment

[0189] Taking downlink beam alignment as an example, beam alignment can be roughly divided into two stages. The first stage is when the UE accesses the network, the initial transmission beam from the base station to the UE is initially trained. The second stage is after the UE establishes a connection, the fine transmit and receive beam pairs from the base station to the UE are trained. The beam training in the second stage is mainly completed through CSI measurement and feedback.

[0190] In the first phase, the base station periodically transmits SSBs, and in each SSB transmission cycle, it transmits a set of SSBs in a beam scanning manner. The UE measures the reference signal carried by the SSB and reports the index of the SSB with higher received energy so that the base station can determine its transmission beam. The UE reports the SSB index according to the rules specified in the protocol. Each SSB corresponds to a set of Physical Random Access Channel (PRACH) resources. The UE transmits the preamble for initial access on the corresponding PRACH resources, representing the UE reporting the corresponding SSB index. For the second phase, the Channel State Information (CSI) acquisition process in Release 15 (Rel-15) NR Uu is detailed in [link to documentation]. Figure 5 The base station configures CSI reporting parameters and triggers CSI reporting. The UE performs CSI measurements and reports based on the base station's configuration information. The base station adjusts uplink and downlink beam transmission parameters based on the UE's results. Each CSI reporting configuration indicates the type of CSI reporting (CSI quantity), including parameters indicating beams such as CRI and SSB index, as well as other parameter types such as Precoding Matrix Indicator (PMI), RI, CQI, L1, RSRP, SINR, and i1.

[0191] For uplink beam training, the base station configures a Sounding Reference Signal (SRS) resource for the UE to perform uplink beam training. The UE then autonomously transmits SRS on the corresponding SRS resource to perform beam training.

[0192] In addition, for beam training on the base station / UE side, the base station / UE can independently select the training beam.

[0193] 12. Beam Indication

[0194] For uplink beam indication, the base station indicates the beam direction adopted by the UE on the UL scheduling resources, and the beam direction is represented by the SRS Resource Indicator (SRI). For downlink beam indication, the base station indicates the beam direction on the DL scheduling resources so that the UE can determine its receiving beam. The downlink beam direction is indicated by the associated TCI, where the TCI reflects information such as CRI and SSB index.

[0195] It should be noted that the AI ​​model in this application embodiment may also be referred to as an AI unit, machine learning (ML) model, ML unit, AI structure, AI function, AI characteristic, machine learning model, neural network, neural network function, neural network functionality, etc. Alternatively, an AI unit may refer to a processing unit capable of implementing specific algorithms, formulas, processing flows, capabilities, etc., related to AI. An AI unit may also be a processing method, algorithm, function, module, or unit for a specific dataset. Furthermore, an AI unit may be a processing method, algorithm, function, module, or unit running on AI / ML related hardware such as GPUs, NPUs, TPUs, and ASICs. This application embodiment does not specifically limit these aspects. Optionally, the specific dataset includes at least one of the inputs and outputs of the AI ​​unit.

[0196] 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 dataset associated with an AI unit, or an identifier of a specific scenario, environment, channel characteristics, or device related to AI / ML, or an identifier of a function, feature, capability, or module related to AI / ML. This application embodiment does not specifically limit this.

[0197] Optionally, the index of an AI model can be described in various ways, such as a functional ID and / or a model ID, a physical ID, a logical ID, a global ID, or a local ID.

[0198] Furthermore, in the embodiments of this application, AI can also be represented as machine learning, which has various implementation methods, such as neural networks, decision trees, support vector machines, Bayesian classifiers, etc. The embodiments of this application do not specifically limit this.

[0199] It should also be noted that the cell involved in the embodiments of this application can be replaced by cellgroup, frequency layer, tracking area (TA), TRP, network node, carrier, bandwidth, subband, or bandwidth part (BWP), etc. Furthermore, the first cell involved in the embodiments of this application may include at least one of the following: source cell, target cell, currently camped cell, currently accessed cell, primary cell (PCell), and secondary cell (SCell).

[0200] The SSB and SS / PBCH block mentioned in the embodiments of this application can be used interchangeably, or can be referred to by other names, that is, any module containing at least some synchronization signals, broadcast signals or other downlink broadcast signals or their control channels.

[0201] The server involved in the embodiments of this application can be a device used for training or predicting or providing AI-related information, or it can be a third server, or it can be a device provided by an over-the-top (OTT) service provider, a third-party service provider, or the Internet.

[0202] The transmission method provided in this application will be described in detail below with reference to the accompanying drawings and through some embodiments and application scenarios.

[0203] Please see Figure 6 , Figure 6 This is a flowchart of a transmission method provided in an embodiment of this application. This method can be executed by a first device, such as... Figure 6 As shown, it includes the following steps:

[0204] Step 601: The first device acquires first information, which is information obtained based on an AI model;

[0205] Step 602: The first device performs a first transmission based on the first information, and the transmission mode corresponding to the first transmission is either a half-duplex transmission mode or a full-duplex transmission mode.

[0206] The first piece of information includes at least one of the following:

[0207] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0208] At least one piece of spatial information;

[0209] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0210] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[0211] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0212] Resources for at least one protective belt;

[0213] At least one parameter related to uplink transmit power;

[0214] At least one piece of interference information.

[0215] In this embodiment, the first device may 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 may obtain the first information by performing inference based on the AI ​​model, or the first device may receive the first information from a second device. For instance, the second device may obtain the first information by performing inference based on the AI ​​model and then send the first information to the first device. The second device may include a terminal, a network-side device, or a server, etc. It is understood that when both the first device and the second device are terminals, the first device and the second device are different terminals; when both the first device and the second device are network-side devices, the first device and the second device are different network-side devices.

[0216] Full-duplex transmission modes may include enhanced full-duplex modes, sub-band full-duplex modes, etc. In some alternative embodiments, the first transmission mode may include a transmission mode under at least one spatial information, or the first transmission mode may include a transmission mode under at least one signal quality strength (e.g., Reference Signal Receiving Power (RSRP)) range.

[0217] Spatial information may include, but is not limited to, at least one of the following: Transmission Configuration Indication (TCI), beam information, reference signal information (e.g., reference signal index), QCL, spatial information, spatial characteristics, antenna panel, TRP, etc. Reference signals may include at least one of SSB, CSI-RS, and SRS, etc.

[0218] It should also be noted that spatial information can also be represented as spatial characteristics, beam, QCL, QCL source spatial attributes, spatial characteristics, TCI, TCI state, TRP, RS, SSB, panel, and other concepts.

[0219] The first performance information can be performance information related to transmission in full-duplex transmission mode, such as at least one of the following: the number of transmissions in full-duplex transmission mode, the probability of successful transmission in full-duplex transmission mode, the probability of transmission failure in full-duplex transmission mode, and the number of transmission failures in full-duplex transmission mode. In some optional embodiments, the first performance information may include performance information under at least one spatial domain information, or the first performance information may include performance information under at least one signal quality strength (e.g., RSRP) range, or performance information over a time period.

[0220] The first transmission parameter may be, but is not limited to, at least one of the following: resources, number of transmissions, and number of retransmissions corresponding to uplink transmission. It should be noted that the first transmission parameter may correspond to full-duplex transmission mode; that is, the first transmission parameter is the transmission parameter for uplink transmission in full-duplex transmission mode. For example, uplink transmission may include, but is not limited to, PRACH, Physical Uplink Control Channel (PUCCH), Dynamic Grant (DG) Physical Uplink Sharing Channel (PUSCH), Configured Grant (CG) PUSCH, and Sounding Reference Signal (SRS).

[0221] In some optional embodiments, the first transmission parameters may include transmission parameters for uplink transmission under at least one spatial information, or the first transmission parameters may include transmission parameters for uplink transmission under at least one RSRP range.

[0222] The second transmission parameter may be, but is not limited to, at least one of the following: resources, number of transmissions, and number of retransmissions corresponding to downlink transmission. It should be noted that the second transmission parameter may correspond to a full-duplex transmission mode, that is, the second transmission parameter is the transmission parameter for downlink transmission in full-duplex transmission mode. In some optional embodiments, the second transmission parameter may include transmission parameters for downlink transmission under at least one spatial information, or the second transmission parameter may include transmission parameters for downlink transmission under at least one RSRP range.

[0223] For example, downlink transmission may include, but is not limited to, SSB, CSI-RS, Physical Downlink Control Channel (PDCCH), Physical Downlink Shared Channel (PDSCH), Semi-Persistent Scheduling (SPS) PDSCH, Positioning Reference Signal (PRS), etc.

[0224] The resources of the guard band (GB) may include the location, length, and size of the guard band. In some optional embodiments, the resources of the guard band may include guard band resources under at least one spatial information, or the resources of the guard band may include guard band resources under at least one signal quality strength (e.g., RSRP) range, or the resources of the guard band may include at least one guard band resource corresponding to the uplink transmit power.

[0225] The relevant parameters of uplink transmit power may include, but are not limited to, at least one of the following: target uplink transmit power, target receive power value, maximum transmit power, power boost value, and power backoff value. In some optional embodiments, the relevant parameters of uplink transmit power may include at least one uplink transmit power relevant parameter under spatial information, or the relevant parameters of uplink transmit power may include at least one uplink transmit power relevant parameter under at least one signal quality strength (e.g., RSRP) range.

[0226] It should be noted that when predicting relevant parameters of transmission power based on an AI model, the input information of the AI ​​model may include interference information, the battery level of the first device, the type of the first device, and other information.

[0227] Interference information may include, but is not limited to, at least one of self-interference information, mutual interference information, and interference cancellation information. For example, self-interference information may include the magnitude or intensity of self-interference; mutual interference information may include the magnitude or intensity of mutual interference; and interference cancellation information may include interference signal information, such as the signal information of self-interference. In some optional embodiments, when the interference magnitudes are sorted in descending order, the interference information may include at least one of the interference information with the first N1 largest interference magnitudes and the interference information with the last N1 largest interference magnitudes, where N1 and N2 are both positive integers.

[0228] In some alternative embodiments, when the interference information includes only self-interference information, the AI ​​model-based inference can be performed by the first device.

[0229] For example, when the first device needs to perform full-duplex transmission, transmission parameters for full-duplex transmission can be obtained based on an AI model. These parameters include uplink and downlink transmission resources, spatial information, uplink transmit power parameters, and guard band resources. This helps obtain more suitable transmission parameters for full-duplex transmission, and full-duplex transmission can then be performed based on these parameters, improving transmission performance. Alternatively, when the first device needs to transmit, a transmission mode can be obtained based on an AI model. This helps obtain a more suitable transmission mode, and transmission can then be performed using this mode, further improving transmission performance. In some optional embodiments, when obtaining the transmission mode based on an AI model, transmission parameters under that transmission mode can also be obtained based on the AI ​​model, allowing transmission to be performed using both the obtained transmission mode and parameters.

[0230] In some alternative embodiments, the first information may also be referred to as full-duplex transmission information.

[0231] It should be noted that the first device performing the first transmission based on the first information may include the first device directly performing the first transmission based on the first information. For example, if the first information includes at least one of the first transmission parameters and the second transmission parameters, the first device may directly perform the first transmission based on the first information. Alternatively, the first device may determine target information based on the first information and perform the first transmission based on the target information. For example, if the first information includes at least one spatial information, at least one first performance information, etc., the first device may determine transmission mode, transmission resources, etc., based on the first information and perform the first transmission based on the determined transmission mode, transmission resources, etc.

[0232] The embodiments of this application are illustrated below with examples:

[0233] For example, this embodiment obtains a first transmission mode based on an AI model, so that the first device can select the corresponding transmission mode for transmission according to the first transmission mode, which can improve the performance of uplink and downlink transmission and improve system performance.

[0234] For example, this embodiment obtains spatial information based on an AI model, so that the first device can select the corresponding uplink or downlink transmission resources for transmission according to the spatial information. The direction corresponding to the spatial information can reduce self-interference between uplink and downlink, or reduce mutual interference between uplink and downlink transmissions of different users, thereby improving the success rate of full-duplex transmission. At the same time, it can reduce retransmissions after full-duplex failures caused by interference and reduce the power consumption of the first device.

[0235] For example, this embodiment obtains performance information related to transmission in full-duplex transmission mode, namely first performance information, based on an AI model. Thus, the first device can select a suitable transmission mode or transmission resources based on the first performance information, which is beneficial to improving the success rate and transmission performance of full-duplex transmission.

[0236] For example, this embodiment obtains the uplink transmission parameters (i.e., the first transmission parameters) and the downlink transmission parameters (i.e., the second transmission parameters) based on the AI ​​model, such as the uplink transmission resources and the downlink transmission resources. Thus, the first device can directly perform full-duplex transmission based on the uplink transmission parameters and the downlink transmission parameters, thereby simplifying the process of selecting uplink and downlink transmission parameters and improving the efficiency of full-duplex transmission.

[0237] For example, this embodiment obtains the guard band resources based on an AI model, which helps to reduce self-interference between uplink and downlink, or reduce mutual interference between uplink and downlink transmissions of different users, thereby improving the performance of full-duplex transmission and reducing resource overhead caused by the guard band.

[0238] For example, this embodiment obtains relevant parameters of uplink transmit power based on an AI model, which helps to reduce self-interference between uplink and downlink, or reduce mutual interference between uplink and downlink transmissions of different users, thereby ensuring the performance of uplink transmission in full-duplex transmission and improving the performance of downlink reception.

[0239] For example, this embodiment obtains interference information based on an AI model. This interference information can be used to suppress or eliminate self-interference between uplink and downlink, or mutual interference between uplink and downlink transmissions of different users, thereby improving the performance of full-duplex transmission.

[0240] In summary, in this embodiment, the first device acquires first information, which is information obtained based on an AI model; and performs a 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. The first information includes at least one of the following: a first transmission mode, which includes a half-duplex transmission mode or a full-duplex transmission mode; at least one spatial information; at least one first performance information, which is performance information related to transmission in full-duplex transmission mode; at least one first transmission parameter, which is an uplink transmission parameter; at least one second transmission parameter, which is a downlink transmission parameter; at least one guard band resource; at least one uplink transmit power related parameter; and at least one interference information. That is, this embodiment obtains the transmission mode or transmission-related parameters based on an AI model for transmission, which helps to ensure transmission performance.

[0241] Optionally, the first device acquires the first information, including:

[0242] The first device receives the first information from the second device;

[0243] or,

[0244] The first device obtains initial information based on an AI model.

[0245] In some implementations, the second device can perform inference based on the AI ​​model to obtain the first information and send the obtained first information to the first device. Since AI inference often has high requirements for device performance or computing power, performing AI inference through the second device can help reduce the performance requirements of the first device or save the computing power resources of the first device.

[0246] For example, when the first device is a terminal, the terminal can receive the first information from the network-side device or the server and perform the first transmission based on the first information. This helps to reduce the performance requirements of the terminal or save the computing resources of the terminal. When the first device is a network-side device, the network-side device can receive the first information from the server and perform the first transmission based on the first information. This helps to reduce the performance requirements of the network-side device or save the computing resources of the network-side device.

[0247] In other implementations, the first device can obtain the first information by reasoning based on the AI ​​model and then perform the first transmission based on the obtained first information. Since the AI ​​reasoning is performed by the device that needs to use the first information for transmission, this not only reduces transmission latency but also helps to save the resource overhead of transmitting the first information.

[0248] Optionally, the airspace information includes at least one of the following: airspace information corresponding to downlink transmission and airspace information corresponding to uplink transmission.

[0249] The spatial information corresponding to downlink transmission may include, but is not limited to, at least one of the following: TCI, SSB, CSI-RS, and beam information corresponding to uplink transmission.

[0250] For example, the spatial information corresponding to downlink transmission can be used only for downlink transmission (i.e., DL only); the spatial information corresponding to downlink transmission can be used only for uplink transmission (i.e., UL only).

[0251] Optionally, the first performance information includes at least one of the following:

[0252] The probability of successful transmission in full-duplex mode;

[0253] The probability of transmission failure in full-duplex transmission mode;

[0254] The number of transmission failures in full-duplex transmission mode.

[0255] Optionally, the first transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions;

[0256] or,

[0257] The second transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions.

[0258] For example, time-domain resources may include, but are not limited to, at least one of slots, symbols, and subframes. Frequency-domain resources may include, but are not limited to, at least one of BWPs, subbands, resource blocks (RBs), RB sets, and carriers. Spatial-domain resources may include, but are not limited to, at least one of TCI states, SSBs, CSI-RS, QCLs, and beams.

[0259] It is understood that the time domain resources, frequency domain resources, spatial domain resources, and number of transmissions or retransmissions included in the first transmission parameter represent the frequency domain resources, spatial domain resources, and number of transmissions or retransmissions corresponding to the uplink transmission, respectively; and the time domain resources, frequency domain resources, spatial domain resources, and number of transmissions or retransmissions included in the second transmission parameter represent the frequency domain resources, spatial domain resources, and number of transmissions or retransmissions corresponding to the downlink transmission, respectively.

[0260] Optionally, the resources of the guard band include at least one of the following: the frequency domain location of the guard band, and the frequency domain size of the guard band.

[0261] For example, the frequency domain location of the guard band may include, but is not limited to, at least one of the start and end positions of the guard band. The frequency domain size of the guard band may include the length of the guard band or the number of frequency domain units, etc.

[0262] Optionally, the relevant parameters of the uplink transmit power include at least one of the following: target uplink transmit power, target receive power value, maximum transmit power, power boost value, and power backoff value.

[0263] Optionally, the interference information includes at least one of the following: interference intensity information, interference signal information.

[0264] For example, interference intensity information may include interference magnitude, such as the magnitude of self-interference or mutual interference within a specific resource, or the magnitude of self-interference or mutual interference within a specific uplink transmit power or uplink transmit power range; or the magnitude of self-interference or mutual interference within a specific beam or QCL. Interference signal information can be used to reduce or eliminate interference.

[0265] Optionally, the interference strength information includes at least one of the following: self-interference strength, mutual interference strength, and indication information used to indicate whether the interference strength meets the corresponding threshold.

[0266] For example, self-interference strength may include at least one of the following: self-interference strength at a specific resource, self-interference strength at a specific uplink transmit power or uplink transmit power range, and self-interference strength at a specific beam or QCL. Mutual interference strength may include at least one of the following: mutual interference strength at a specific resource, mutual interference strength at a specific uplink transmit power or uplink transmit power range, and mutual interference strength at a specific beam or QCL.

[0267] The interference strength meeting the corresponding threshold can include the interference strength being higher than the corresponding threshold, or the interference strength being less than or equal to the corresponding threshold. For example, the indication information indicating whether the interference strength meets the corresponding threshold can include at least one of the following: indication information for indicating whether the self-interference strength meets the corresponding threshold, and indication information for indicating whether the mutual interference strength meets the corresponding threshold. It should be noted that the threshold corresponding to the self-interference strength and the threshold corresponding to the mutual interference strength can be the same or different.

[0268] Optionally, the interference signal information includes at least one of the following: at least one reverse signal of the transmitted signal, and at least one preprocessing information corresponding to the transmitted signal.

[0269] The transmitted signal can be understood as the signal sent by the first device for transmission.

[0270] For example, the preprocessing information may include a pre-distortion amount to counteract interference.

[0271] Optionally, the first information may also include at least one probability information;

[0272] Among them, the probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

[0273] In other words, the first information may also include at least one of the following: probability information corresponding to at least one spatial information, probability information corresponding to at least one transmission mode, probability information corresponding to at least one first transmission parameter, probability information corresponding to at least one second transmission parameter, probability information corresponding to at least one guard band resource, and probability information corresponding to at least one uplink transmit power related parameter.

[0274] For example, the probability information corresponding to each spatial information can be used to indicate the probability of transmission using that spatial information. The probability information corresponding to each transmission mode can be used to indicate the probability of transmission using that transmission mode. The probability information corresponding to each first transmission parameter is used to indicate the probability of uplink transmission using that first transmission parameter. The probability information corresponding to each second transmission parameter is used to indicate the probability of downlink transmission using that second transmission parameter. The probability information corresponding to each guard band resource is used to indicate the probability of transmission using the resources of that guard band. The relevant parameters of each uplink transmit power are used to indicate the probability of transmission using the relevant parameters of that uplink transmit power.

[0275] It should be noted that the parameters related to at least one transmission mode, at least one spatial information, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power corresponding to the probability information may be the same as the corresponding parameters in the first information; or, they may include the corresponding parameters in the first information; or, they may be different from the corresponding parameters in the probability information.

[0276] In this embodiment, the first information also includes at least one probability information, which is beneficial for the first device to select more appropriate parameters for transmission based on the probability information.

[0277] The following examples illustrate different scenarios:

[0278] Scenario 1: Network-side equipment (e.g., base stations, TRPs, or core network equipment) can obtain transmission information (i.e., first information) for 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 transmit power, a specific guard band, etc., based on an AI model, and notify the corresponding terminal. The terminal can then directly or indirectly use this transmission information for transmission.

[0279] Scenario 2: The terminal can obtain transmission information or specific interference information (i.e., first information) between itself and at least one network-side device (e.g., base station, TRP, or core network device) based on an AI model. This transmission information includes specific beam direction, specific reference signal, specific reference point, specific pathloss or RSRP range, specific transmission mode, specific frequency domain resources, specific uplink transmit power, specific guard band, etc. The terminal can then directly or indirectly use this transmission information or interference information for transmission.

[0280] For example, the first information may include at least one of the following:

[0281] 1) Transmission information corresponding to a specific terminal, for example, may include at least one of the following:

[0282] One or a set of spatial information corresponding to the full-duplex transmission between a specific terminal and a target cell or network node;

[0283] The transmission mode corresponding to the transmission between a specific terminal and a target cell or network node, including half-duplex or full-duplex;

[0284] The probability of successful or failed downlink reception for full-duplex transmission between a specific terminal and a target cell or network node;

[0285] One or a group of first resources corresponding to full-duplex transmission between a specific terminal and a target cell or network node, wherein the first resource is the resource for uplink transmission;

[0286] One or a group of second resources corresponding to full-duplex transmission between a specific terminal and a target cell or network node, wherein the second resource is a resource for downlink transmission;

[0287] One or a set of guard band resources corresponding to full-duplex transmission between a specific terminal and a target cell or network node;

[0288] The relevant parameters of the uplink transmit power of one or a group of uplink transmissions corresponding to full-duplex transmission between a specific terminal and a target cell or network node.

[0289] 2) Transmission information corresponding to a set of terminals, for example, may include at least one of the following:

[0290] A terminal of a specific beam or TRP performs full-duplex transmission of one or a set of corresponding spatial information;

[0291] The transmission mode for a specific beam or TRP terminal is the corresponding transmission mode, including half-duplex or full-duplex;

[0292] The probability of successful or failed downlink reception for a specific beam or TRP terminal performing full-duplex transmission;

[0293] A specific beam or TRP terminal performs full-duplex transmission of one or a group of first resources, where the first resource is the resource for uplink transmission;

[0294] For a specific beam or TRP terminal to perform full-duplex transmission, there is one or a group of second resources corresponding to the second resources, which are resources for downlink transmission;

[0295] One or a set of guard band resources corresponding to full-duplex transmission of a specific beam or TRP terminal;

[0296] The relevant parameters of the uplink transmit power for one or a group of uplink transmissions corresponding to full-duplex transmissions of a specific beam or TRP terminal.

[0297] 3) Transmission information corresponding to a specific area, for example, may include at least one of the following:

[0298] Terminals within a specific area transmit one or a set of spatial information in full-duplex mode.

[0299] The transmission mode corresponding to the transmission of data by terminals within a specific area, including half-duplex or full-duplex;

[0300] The probability of successful or unsuccessful downlink reception for a terminal within a specific area performing full-duplex transmission;

[0301] One or a group of first resources corresponding to full-duplex transmission of terminals within a specific area, wherein the first resource is the resource for uplink transmission;

[0302] One or a group of second resources corresponding to full-duplex transmission of terminals within a specific area; the second resources are resources for downlink transmission.

[0303] One or a set of guard band resources corresponding to full-duplex transmission by terminals within a specific area;

[0304] The relevant parameters of the uplink transmit power for one or a group of uplink transmissions corresponding to full-duplex transmissions by terminals within a specific area.

[0305] Specific areas may include cells, cell groups, time advance groups (TAGs), tracking areas, or radio access network notification areas (RAN Notification Areas, RNAs), etc.

[0306] In some optional embodiments, a specific area may include the area corresponding to at least one cell such as the source cell, target cell, currently camped cell, currently accessed cell, Pcell, and Scell.

[0307] 4) Transmission information for a specific beam direction, a specific TRP, or a specific SSB may include at least one of the following:

[0308] The transmission mode corresponding to full-duplex transmission of a terminal in a specific beam direction, TRP, or SSB, including half-duplex or full-duplex.

[0309] The probability of successful or unsuccessful downlink reception for a terminal performing full-duplex transmission in a specific beam direction, TRP, or SSB.

[0310] A terminal performing full-duplex transmission in a specific beam direction, or a specific TRP or SSB, corresponds to one or a group of first resources, where the first resource is the resource for uplink transmission.

[0311] A second resource or a set of second resources corresponding to full-duplex transmission of a terminal in a specific beam direction, a specific TRP, or a specific SSB. The second resource is a resource for downlink transmission.

[0312] One or a set of guard band resources corresponding to full-duplex transmission of a terminal in a specific beam direction, or a specific TRP or SSB;

[0313] The uplink transmit power related parameters for one or a group of uplink transmissions corresponding to full-duplex transmissions of a terminal with a specific beam direction, a specific TRP, or a specific SSB.

[0314] 5) Transmission information for a specific reference point, which, for example, may include at least one of the following:

[0315] A terminal at a specific reference point performs full-duplex transmission of one or a set of corresponding spatial information.

[0316] The transmission mode corresponding to the terminal at a specific reference point, including half-duplex or full-duplex;

[0317] The probability of successful / failed downlink reception for a terminal at a specific reference point performing full-duplex transmission;

[0318] A terminal at a specific reference point performs full-duplex transmission of one or a group of first resources, where the first resource is the resource for uplink transmission;

[0319] A terminal at a specific reference point performs full-duplex transmission of one or a group of second resources, which are resources for downlink transmission;

[0320] One or a set of guard band resources corresponding to the full-duplex transmission of a terminal at a specific reference point;

[0321] The relevant parameters of the uplink transmit power for one or a group of uplink transmissions corresponding to full-duplex transmissions at a terminal at a specific reference point.

[0322] It should be noted that the transmission information for a specific reference point will be notified to the UE within the cell;

[0323] 6) Transmission information corresponding to a specific pathloss range or a specific RSRP range, which, for example, may include at least one of the following:

[0324] The pathloss or RSRP values ​​are within a specific pathloss range or a specific RSRP range, and the terminal performs full-duplex transmission of one or a set of spatial information corresponding to this.

[0325] The transmission mode corresponding to the transmission of terminals whose pathloss or RSRP values ​​are within a specific pathloss range or a specific RSRP range includes half-duplex or full-duplex.

[0326] The probability of successful or failed downlink reception for a terminal that performs full-duplex transmission when the pathloss or RSRP value is within a specific pathloss range or a specific RSRP range.

[0327] The pathloss or RSRP value is within a specific pathloss range or a specific RSRP range. The first resource is one or a group of first resources corresponding to the full-duplex transmission of the terminal. The first resource is the resource for uplink transmission.

[0328] The pathloss or RSRP value is within a specific pathloss range or a specific RSRP range. The terminal performs full-duplex transmission for one or a group of second resources, which are resources for downlink transmission.

[0329] The pathloss or RSRP value is within a specific pathloss range or a specific RSRP range, corresponding to one or a group of guard band resources for full-duplex transmission by the terminal.

[0330] The pathloss or RSRP values ​​are parameters related to the uplink transmit power of one or a group of uplink transmissions corresponding to full-duplex transmissions of terminals within a specific pathloss range or a specific RSRP range.

[0331] In some alternative embodiments, pathloss or RSRP refers to the pathloss or RSRP between the terminal and the base station, which may be the base station of the first cell.

[0332] 7) Transmission mode, exemplarily, may include at least one of the following:

[0333] Transmission mode under specific time domain resources;

[0334] Transmission modes under specific frequency domain resources;

[0335] Transmission modes under specific TCI or beam;

[0336] Transmission mode at a specific uplink transmit power;

[0337] Transmission mode under specific cell signal strength (e.g., specific RSRP);

[0338] Transmission mode under a specific interference signal strength (e.g., Received Signal Strength Indication (RSSI)).

[0339] 8) Uplink transmit power, which, for example, may include at least one of the following:

[0340] Uplink transmit power for full-duplex transmission under specific time-domain resources;

[0341] Uplink transmit power for full-duplex transmission under specific frequency domain resources;

[0342] Uplink transmit power for full-duplex transmission under specific TCI or beam conditions;

[0343] Uplink transmit power for full-duplex transmission under specific cell signal strength;

[0344] Uplink transmit power for full-duplex transmission under specific interference signal strength;

[0345] Uplink transmit power for full-duplex transmission under specific guard band resources.

[0346] 9) The relevant performance characteristics of full-duplex transmission may, for example, include at least one of the following:

[0347] i) The probability of successful reception, or reception error or failure, may include at least one of the following:

[0348] The probability of successful or unsuccessful reception of downlink signals in full-duplex transmission under specific time domain resources;

[0349] The probability of successful or unsuccessful reception of downlink signals in full-duplex transmission under specific frequency domain resources;

[0350] The probability of success or failure of downlink signal transmission in full-duplex mode under a specific TCI or beam;

[0351] The probability of success or failure of downlink signal transmission in full-duplex mode at a specific uplink transmit power;

[0352] The probability of successful or unsuccessful reception of downlink signals in full-duplex transmission under specific cell signal strength;

[0353] The probability of successful or unsuccessful reception of downlink signals in full-duplex transmission under specific interference signal strength;

[0354] The probability of successful or unsuccessful reception of downlink signals in full-duplex transmission under specific guard band resources.

[0355] Successful reception can also be expressed as successful decoding, successful decryption, or successful detection.

[0356] Reception error or failure can also be expressed as decoding failure, decoding error, decoding failure, decoding error, or detection error, etc.

[0357] ii) The number of received errors / failures may include at least one of the following:

[0358] The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources;

[0359] The number of downlink signal reception failures in full-duplex transmission under a specific TCI or beam;

[0360] The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power;

[0361] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[0362] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[0363] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources;

[0364] 10) The resources of the protection zone, by way of example, may include at least one of the following:

[0365] Guard band resources for full-duplex transmission under specific time domain resources;

[0366] Guard band resources for full-duplex transmission under specific frequency domain resources;

[0367] Guard band resources for full-duplex transmission under specific TCI or beam conditions;

[0368] Guard band resources for full-duplex transmission at a specific uplink transmit power;

[0369] Guard band resources for full-duplex transmission under specific cell signal strength;

[0370] Guard band resources for full-duplex transmission under specific interference signal strength.

[0371] 11) One or a set of interfering information, exemplarily, may include at least one of the following:

[0372] Interference information transmitted in full duplex mode under specific time domain resources;

[0373] Interference information transmitted in full duplex under specific frequency domain resources;

[0374] Sources of interference information transmitted in full-duplex mode under specific TCI or beam conditions;

[0375] Interference information transmitted in full duplex at a specific uplink transmit power;

[0376] Interference information transmitted in full duplex under specific cell signal strength;

[0377] Interference information transmitted in full duplex mode under a specific protection band.

[0378] It should also be noted that the first information may include information required for transmission (e.g., full-duplex transmission), or information related to full-duplex transmission performance; or, it may include transmission information inferred at different granularities (e.g., different beams, different RSRPs, etc.). In this embodiment, transmission is performed based on transmission information inferred from the AI ​​model (e.g., full-duplex transmission), which is beneficial to improve transmission performance, reduce overhead, and reduce latency.

[0379] Optionally, the input information for the AI ​​model includes at least one of the following:

[0380] Signal information, distance information, path loss information, secondary performance information, maximum uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side equipment status information, satellite status information, sensing information, non-terrestrial network (NTN) base station information, channel information, and time information; among which, the secondary performance information is performance information related to transmission in full-duplex transmission mode.

[0381] It should be noted that one of the terminal and network-side devices is the first device, and the other is the corresponding device that performs the transmission for the first device.

[0382] Optionally, the signal information includes at least one of the following: signal strength information, signal quality information, and interference signal strength information.

[0383] For example, signal strength information may include, but is not limited to, at least one of RSRP, Reference Signal Received Quality (RSRQ), and RSSI. Signal quality information may include, but is not limited to, at least one of Signal Noise Ratio (SNR), Signal to Interference Plus Noise Ratio (SINR), and latency. Interference signal strength information may include, but is not limited to, at least one of RSRP and RSSI. Interference may include, but is not limited to, at least one of self-interference, mutual interference, inter-cell interference, and intra-cell interference.

[0384] Optionally, the signal strength information includes at least one of the following:

[0385] Uplink signal reception strength information between the first and second devices;

[0386] Downlink signal reception strength information between the first device and the second device;

[0387] or,

[0388] Signal quality information includes at least one of the following:

[0389] Signal quality information of the uplink signal between the first and second devices;

[0390] Signal quality information of the downlink signal between the first device and the second device;

[0391] or,

[0392] Interference signal strength information includes at least one of the following:

[0393] Self-interference intensity information of the first device;

[0394] Mutual interference strength information of the first device;

[0395] Self-interference intensity information of the second device;

[0396] Interference strength information of the second device.

[0397] For example, one of the first device and the second device is a terminal, and the other is a network-side device, such as a network node of the first cell, wherein the first cell is the source cell of the terminal, the target cell of the terminal, the cell where the terminal is currently camped, the cell where the terminal is currently accessing, the PCell of the terminal, and the SCell of the terminal.

[0398] The uplink signal between the first device and the second device may include, but is not limited to, at least one of uplink probe signals, uplink reference signals, and uplink synchronization signals, such as SRS. The received signal strength and signal quality information of the uplink signal between the first device and the second device can be measured and obtained by the network-side device. For example, if the received signal strength and signal quality information of the uplink signal between the first device and the second device are used by the terminal for AI inference, the network-side device can measure and obtain the received signal strength and signal quality information of the uplink signal between the first device and the second device and send it to the terminal.

[0399] The downlink signal between the first device and the second device may include, but is not limited to, at least one of downlink broadcast signals, downlink synchronization signals, and downlink reference signals, such as SSB, CSI-RS, and TRS. The received signal strength and signal quality information of the downlink signal between the first device and the second device can be obtained by the terminal measurement. For example, if the received signal strength and signal quality information of the downlink signal between the first device and the second device are used by the network-side device for AI inference, the terminal can measure and obtain the received signal strength and signal quality information of the downlink signal between the first device and the second device and report it to the network-side device.

[0400] The mutual interference strength information of the first device may include at least one of the following: mutual interference strength information of uplink or downlink signals between the first device and the second device, and mutual interference strength information of uplink or downlink signals between the first device and the third device; wherein, the third device and the first device are of the same type, 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 the source cell, and the third device is a network node of the target cell or Pcell and Scell.

[0401] The mutual interference strength information of the second device may include at least one of the following: mutual interference strength information of uplink or downlink signals between the second device and the first device, and mutual interference strength information of uplink or downlink signals between the second device and the fourth device; wherein, the fourth device and the second device are of the same type, 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 the source cell, and the fourth device is a network node of the target cell or Pcell and Scell.

[0402] Optionally, the distance information includes at least one of the following:

[0403] The distance between the first terminal and the network node of the first cell;

[0404] The distance between network nodes in the source cell and network nodes in the target cell;

[0405] The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell;

[0406] The distance between the first terminal and the second terminal;

[0407] or,

[0408] Path loss information includes at least one of the following:

[0409] Path loss between the first terminal and the network node of the first cell;

[0410] Path loss between network nodes in the source cell and network nodes in the target cell;

[0411] Path loss between network nodes of Pcell and network nodes of Scell;

[0412] 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.

[0413] 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.

[0414] 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.

[0415] Optionally, the second performance information includes at least one of the following:

[0416] The number of downlink signal reception failures in full-duplex transmission under specific time domain resources;

[0417] The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources;

[0418] The number of downlink signal reception failures in full-duplex transmission under specific spatial information;

[0419] The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power;

[0420] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[0421] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[0422] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

[0423] For example, full-duplex transmission may include full-duplex transmission between the terminal and a network node in the first cell. Specific spatial information may include, but is not limited to, at least one of specific TCI and specific beam. Specific cell signal strength may include, but is not limited to, specific RSRP. Specific interference signal strength may include, but is not limited to, specific RSSI.

[0424] Optionally, the area information includes at least one of the following: Transmitter / Receiver Point (TRP) identifier, TRP group identifier, cell identifier, cell group identifier, Time Advance Group (TAG) identifier, Tracking Area (TA) identifier, and Radio Access Network Notification Area (RAN Notification Area) identifier.

[0425] For example, the TRP identifier may include at least one of the following: source TRP, target TRP, currently residing TRP, currently accessing TRP, primary TRP, and secondary TRP.

[0426] For example, the TRP group identifier may include at least one group identifier such as source TRP, target TRP, currently residing TRP, currently accessing TRP, primary TRP, and secondary TRP.

[0427] For example, the cell identifier may include at least one of the following: source cell, target cell, currently camped cell, currently accessing cell, Pcell, and Scell.

[0428] For example, the cell identifier group may include at least one of the following: the cell group where the source cell is located, the cell group where the target cell is located, the cell group where the currently camped cell is located, the cell group where the currently accessed cell is located, the cell group where the Pcell is located, and the cell group where the Scell ​​is located.

[0429] For example, the TAG identifier may include at least one of the following group identifiers: the TAG of the source cell, the TAG of the target cell, the TAG of the currently camped cell, the TAG of the currently accessed cell, the TAG of the Pcell, and the TAG of the Scell.

[0430] For example, the TA identifier may include at least one of the following: the TA of the source cell, the TA of the target cell, the TA of the currently camped cell, the TA of the currently accessed cell, the TA of the Pcell, and the TA of the Scell.

[0431] For example, the RNA identifier may include at least one of the following: the RNA of the source cell, the RNA of the target cell, the RNA of the currently resident cell, the RNA of the currently accessed cell, the RNA of the P cell, and the RNA of the S cell.

[0432] For frequency domain information, exemplary examples include frequency bands, frequency zones, frequency points, carrier frequencies, frequency layers, or BWPs. For instance, frequency domain information may include at least one of the following: source cell, target cell, currently camped cell, currently accessed cell, Pcell, and Scell, in which at least one frequency band, frequency zone, frequency point, carrier frequency, frequency layer, or BWP is actually operating.

[0433] For example, beam information may include one or a set of reference signal indices, beam indices, or beam directions. For instance, beam information may include the reference signal indices, beam indices, or beam directions actually transmitted between the terminal and the network node of the first cell.

[0434] For latency information, for example, it may include at least one of propagation latency and round-trip time (RTT). For instance, transmission latency may include uplink or downlink signal propagation latency, or signal propagation latency between network nodes. Round-trip time may include the round-trip time between the terminal and a network node in the first cell.

[0435] Optionally, business-related information includes at least one of the following:

[0436] Load status of at least one cell in the first cell;

[0437] Interference situation in at least one cell of the first cell;

[0438] The load status corresponding to at least one spatial feature of the first cell;

[0439] Interference situation corresponding to at least one spatial feature of the first cell;

[0440] The load status of at least one carrier or frequency point in the first cell;

[0441] Interference situation corresponding to at least one carrier and frequency point of the first cell;

[0442] 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.

[0443] It is understandable that when the first device is a terminal, the first cell is the cell of the first device; when the first device is a network-side device, the first device is the network node of the first cell.

[0444] For example, load conditions may include, but are 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. Interference conditions may include, but are not limited to, self-interference measurement value, mutual interference measurement value, maximum or minimum mutual interference link information, beam information of maximum or minimum mutual interference link, maximum or minimum N3 mutual interference link information, beam information of maximum or minimum N3 mutual interference links, etc., where N3 is a positive integer.

[0445] 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.

[0446] or,

[0447] 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.

[0448] or,

[0449] The satellite's status information includes at least one of the following: the satellite's panel orientation, the satellite's speed, and the satellite's direction of movement.

[0450] The terminal's location information can be the terminal's geographic coordinates, such as Global Positioning System (GPS) coordinates, or the terminal's location range information, such as the street where the terminal is located, or the terminal's location information relative to the cell it is camping in, the cell it is accessing, or a certain TRP or a group of TRPs, such as being due east of the cell it is camping in.

[0451] Terminal distribution information may include the number of terminals in different areas (e.g., the stationed cell, the access cell, a certain TRP, or a group of TRPs).

[0452] The direction of movement of the terminal can be an absolute direction, such as 40 degrees east of south; or it can be a relative direction, such as the direction relative to a certain base station or reference point.

[0453] The type of terminal, for example, the power class.

[0454] The network scene information of the terminal, such as indoor hotspot (inH), urban macro (UMa) cell or rural macro (RMa) cell, or homogeneous / heterogeneous network, i.e. whether there is overlapping coverage.

[0455] Information about the environment in which the terminal is located, such as weather information.

[0456] Transmission power information of network-side devices, for example, the actual transmission power of network nodes in the first cell.

[0457] Location information of network-side devices, such as the geographical location information of network nodes in the first cell.

[0458] Environmental information of the network-side devices, such as weather information.

[0459] Sensing information can be understood as information acquired through sensing. For example, sensing information may include, but is not limited to, communication environment information, scene information, channel state information (e.g., line-of-sight (LOS) path, non-line-of-sight (NLOS) path, or obstructions), the number of terminals, etc. For instance, sensing at least one of the following: whether there are obstacles under a specific beam and the number of obstacles; or sensing the number of terminals or devices covered by a specific beam.

[0460] NTN base station information, for example, may include at least one of ephemeris information, the reference position of the cell in the NTN scenario, or its movement trajectory. For example, in a Low-Earth Orbit (LEO) scenario, the cell on Earth moves as the satellite moves, so the cell's movement trajectory can be obtained in this scenario; or, in a Geostationary Orbit (GEO) scenario, the cell on Earth is fixed as the satellite moves, and a reference position can be considered to exist, so the cell's reference position can be obtained in this scenario.

[0461] Channel information, for example, may include multipath information of the channel, such as the first path or strongest path information of the terminal and different base stations or TRPs.

[0462] Time information, for example, can be a precise time, such as 13:25:38; or it can be a time range, such as 13:00 to 14:00, AM / PM, day / night, etc.; or it can be timing information obtained through a first RAT, which can be a different RAT from the RAT used in the first transmission, for example, the first RAT can be Bluetooth, Wi-Fi, 3G, 4G or 5G, etc.

[0463] It should be noted that input information helps improve the accuracy and flexibility of AI model reasoning, thereby improving the performance of the AI ​​model.

[0464] In some optional embodiments, the entity performing AI model inference includes at least one of the following:

[0465] 1) Terminal;

[0466] Since the information held by the terminal is the most up-to-date, having the AI ​​model inference executed by the terminal device ensures that the inference is based on the latest information, thereby improving the reliability of the inference results.

[0467] 2) Network-side equipment;

[0468] For example, network-side equipment includes at least one of a base station, a TRP, and core network equipment (such as core network equipment specifically used for model training).

[0469] Here, the base station or TRP can be the base station or TRP where the terminal is currently camped, the terminal is currently accessing, or the terminal is switching targets or reselecting targets. Performing AI model inference through network-side devices can reduce the complexity, cost, and power consumption of the terminal.

[0470] 3) Server;

[0471] Servers can be devices specifically designed for training, inference, or providing AI-related information. They can also be third-party servers, or devices provided by OTT service providers, third-party service providers, or the internet. Using dedicated servers for AI model inference can improve AI performance while reducing the complexity and cost of network and terminal devices.

[0472] In some optional embodiments, when the terminal performs model inference, the method may further include: the terminal obtaining an AI model from other terminals / network-side devices / servers, and using the AI ​​model to obtain first information based on input information. At least a portion of the input information used for AI model inference may be sent to the terminal by the network-side device, and the signal or channel sending at least a portion of the input information includes at least one of the following: Media Access Control Element (MAC CE), Radio Resource Control (RRC) message, Non-access Stratum (NAS) message, user plane data, Downlink Control Information (DCI) information, System Information Block (SIB), PDCCH, PDSCH, MSG2 information, MSG4 information, and MSGB information.

[0473] In some optional embodiments, when the network-side device performs AI model inference, the method may further include: the network-side device obtaining an AI model from a terminal / other network-side device / server, and using the AI ​​model to obtain first information based on input information. At least a portion of the input information used for AI model inference is reported by the terminal, and the signal or channel reporting at least a portion of the input information includes at least one of the following: MAC CE, RRC message, NAS message, user plane data MSG1 information, MSGA information, MSG3 information, PUCCH, PUSCH, PRACH, SRS.

[0474] In some alternative embodiments, when the server performs AI model inference, at least part of the input information for the AI ​​model inference is indicated by the terminal or network-side device, for example, via OTT messages.

[0475] Optionally, the method further includes:

[0476] The first device obtains the first configuration information;

[0477] The first configuration information includes at least one of the following:

[0478] AI model or AI model identifier;

[0479] The application scope of AI model reasoning;

[0480] The inference cycle of AI models;

[0481] The effective duration of AI model inference;

[0482] Triggering conditions for AI model inference;

[0483] The configuration parameters of the AI ​​model include at least one of the following: the input information of the AI ​​model, the output information of the AI ​​model, the type of the input information of the AI ​​model, and the type of the output information of the AI ​​model.

[0484] The first instruction information is used to indicate whether joint reasoning is supported or required.

[0485] The application scope of AI model inference can be categorized as follows: for example, the frequency domain range in which AI model inference can be applied, or the cell or cell list in which AI model inference can be applied, or the interval in which the terminal is located, or the range of distance between the terminal and the base station.

[0486] The effective duration can include the start and end times of the inference, or it can be a specific time length, such as 1 hour, 2 hours, etc.

[0487] The triggering condition for AI model inference is used to trigger AI model inference. It should be noted that the triggering condition is not the only condition for triggering or activating AI model inference; it can also be combined with other information to trigger or activate AI model inference.

[0488] Joint inference refers to a situation where, when a first device uses an AI model for inference, at least some of the input information of the AI ​​model is provided by other devices. For example, when a terminal uses an AI model for inference, at least some of the input information of the AI ​​model is sent by the network side; when a network-side device uses an AI model for inference, at least some of the input information of the AI ​​model is reported by the terminal; and when a server uses an AI model for inference, at least some of the input information of the AI ​​model is sent by the terminal and / or the network-side device.

[0489] For example, the first device can obtain the first configuration information from the second device and perform AI model inference based on the first configuration information, which is beneficial for more accurate AI inference control.

[0490] Optionally, the method further includes:

[0491] The first device acquires the second instruction information, which is used to indicate the activation or deactivation information of the AI ​​model.

[0492] The first device activates or deactivates the AI ​​model based on the second instruction information.

[0493] For example, when the second instruction information indicates the activation information of the AI ​​model, the first device can activate the AI ​​model based on the second instruction information; when the second instruction information indicates the deactivation information of the AI ​​model, the first device can deactivate the AI ​​model based on the second instruction information.

[0494] In this embodiment, the AI ​​model is activated or deactivated based on the second indication information, which helps to improve the flexibility of AI model activation or deactivation.

[0495] Optionally, the triggering conditions for using AI models for reasoning include at least one of the following:

[0496] The timer used to trigger AI inference timed out;

[0497] Select transmission based on full-duplex transmission configuration;

[0498] The failure probability corresponding to full-duplex transmission is greater than or equal to the first threshold.

[0499] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[0500] The interference signal strength corresponding to full-duplex transmission is greater than or equal to the third threshold.

[0501] The terminal performs cell or TRP reselection;

[0502] The terminal performs cell or TRP handover;

[0503] Business arrives;

[0504] Received instruction information to perform AI inference;

[0505] The terminal's location has changed or the terminal's movement parameters have changed;

[0506] The terminal's spatial information has changed or the transmission filter has changed.

[0507] In this embodiment, at least one of the first threshold, the second threshold, and the third threshold can be predefined by the protocol or configured by the network-side device.

[0508] The timer used to trigger AI inference can be a newly defined, specific timer for triggering AI inference. When the first device detects that this specific timer has expired, it triggers the AI ​​model inference. Understandably, this timer for triggering AI inference can also reuse an existing timer.

[0509] When a full-duplex transmission configuration is selected for transmission—for example, if the network-side device is configured with a dedicated full-duplex transmission configuration—the AI ​​model is triggered to perform inference. This full-duplex transmission configuration can also be referred to as full-duplex transmission parameters.

[0510] When a terminal performs cell or TRP handover, AI model inference is triggered. Specifically, AI model inference may be triggered when cell handover conditions are met. For example, cell handover conditions may include at least one of the following: the measurement result of the source cell (RSRP, RSRQ or RSSI of L1 or L3, etc.) is greater than or less than a first target threshold; the measurement result of the target cell or neighboring cell is better than that of 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; and the load of the source cell is greater than a fourth target threshold.

[0511] The failure probability corresponding to full-duplex transmission is greater than or equal to a first threshold, and for example, it may include at least one of the following:

[0512] The number of downlink signal reception failures in full-duplex transmission under one or a set of time-domain resources is greater than or equal to the first threshold 1;

[0513] The number of downlink signal reception failures in full-duplex transmission under one or a set of frequency domain resources is greater than or equal to the first threshold 2;

[0514] The number of downlink signal reception failures in full-duplex transmission under one or a group of TCI or beam is greater than or equal to the first threshold 3;

[0515] The number of downlink signal reception failures in full-duplex transmission under one or a group of uplink transmit powers is greater than or equal to the first threshold of 4.

[0516] The number of downlink signal reception failures in full-duplex transmission under the signal strength of one or a group of cells is greater than or equal to the first threshold of 5.

[0517] The number of downlink signal reception failures in full-duplex transmission under one or a group of interference signal strengths is greater than or equal to the first threshold of 6.

[0518] The number of downlink signal reception failures in full-duplex transmission under one or a group of guard band resources is greater than or equal to the first threshold 7;

[0519] The number of failed attempts to switch between different transmission modes is greater than or equal to the first threshold of 8.

[0520] Among them, the first threshold 1 to the first threshold 8 can be at least partially the same or at least partially different.

[0521] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, and for example, may include at least one of the following:

[0522] The uplink transmit power of full-duplex transmission under one or a set of time-domain resources is greater than or equal to the second threshold 1;

[0523] The uplink transmit power for full-duplex transmission under one or a set of frequency domain resources is greater than or equal to the second threshold 2;

[0524] The uplink transmit power for full-duplex transmission under one or a group of TCI or beams is greater than or equal to the second threshold 3;

[0525] The uplink transmit power for full-duplex transmission under the signal strength of one or a group of cells is greater than or equal to the second threshold 4;

[0526] The uplink transmit power of full-duplex transmission under one or a group of interference signal strengths is greater than or equal to the second threshold 5;

[0527] The uplink transmit power for full-duplex transmission under one or a group of guard band resources is greater than or equal to the second threshold 6;

[0528] The difference between the transmit power corresponding to full-duplex transmission and the maximum transmit power is greater than or equal to the second threshold 7.

[0529] Among them, the second thresholds 1 to 7 can be at least partially the same or at least partially different.

[0530] For full-duplex transmission to reach its maximum uplink transmit power, for example, it may include at least one of the following:

[0531] The uplink transmit power of full-duplex transmission under one or a set of time-domain resources reaches the corresponding maximum transmit power;

[0532] The uplink transmit power of full-duplex transmission under one or a group of frequency domain resources reaches the corresponding maximum transmit power;

[0533] The uplink transmit power of full-duplex transmission under one or a group of TCI or beams reaches the corresponding maximum transmit power;

[0534] Under the signal strength of one or a group of cells, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power;

[0535] Under the strength of one or a group of interference signals, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power.

[0536] Under one or a group of guard band resources, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power.

[0537] The interference signal strength corresponding to full-duplex transmission is greater than or equal to a third threshold, and can, for example, include at least one of the following:

[0538] The interference signal strength for full-duplex transmission under one or a set of time-domain resources is greater than or equal to the third threshold 1;

[0539] The interference signal strength for full-duplex transmission under one or a set of frequency domain resources is greater than or equal to the third threshold 2;

[0540] The number of downlink signal reception failures in full-duplex transmission under one or a group of TCI or beam is greater than or equal to the third threshold 3;

[0541] The interference signal strength in full-duplex transmission at one or a group of uplink transmit powers is greater than or equal to the third threshold 4;

[0542] The interference signal strength of full-duplex transmission under the RSRP of one or a group of cell signal strengths is greater than or equal to the third threshold 5;

[0543] The interference signal strength for full-duplex transmission under one or a group of protection band resources is greater than or equal to the third threshold 6.

[0544] Among them, the third threshold 1 to the third threshold 6 can be at least partially the same or at least partially different.

[0545] Service arrival can include UL service or data arrival or DL ​​service or data arrival. In some alternative embodiments, it can be a specific type of service arrival, such as a service with high latency requirements or a service with high reliability requirements.

[0546] Instructional information used to instruct the conduct of AI inference can, for example, be instruction information used to instruct the acquisition of first information based on an AI model.

[0547] The terminal's location changes; for example, the terminal moves to a specific location, such as the cell edge; or the change in the terminal's location exceeds a corresponding threshold. The terminal's movement parameters may include at least one of the following: the terminal's movement speed, direction of movement, acceleration, etc. The terminal's movement parameters change; for example, the terminal's speed or acceleration exceeds a corresponding threshold.

[0548] The terminal's spatial information may include beam information, etc. AI inference is triggered when the terminal's spatial information changes, for example, when performing beam failure recovery.

[0549] It should be noted that the triggering condition for using AI models for reasoning can mean that AI reasoning will definitely be triggered as long as at least one of the triggering conditions is met; or it can mean that AI reasoning can be performed as long as at least one of the triggering conditions is met. However, whether AI reasoning is triggered specifically needs to be further considered in conjunction with AI-related capabilities, the application scope of AI model reasoning, and other indications from the network side.

[0550] For example, when at least one of the triggering conditions is met, AI-based inference is immediately triggered; or when at least one of the triggering conditions is met, it indicates that AI-based inference is enabled, but whether to trigger it needs to be determined by taking into account AI-related capabilities, the application scope of AI model inference, and other indications from the network side.

[0551] Optionally, the method further includes:

[0552] The first device performs a first operation, which includes at least one of the following:

[0553] Send a second message, which includes at least one of the following: a first message, at least a portion of the input information of the AI ​​model, and the status information of the first device;

[0554] Revert to using a non-AI method to determine the initial information;

[0555] Trigger adjustments to the AI ​​model;

[0556] Trigger the training of the AI ​​model;

[0557] Trigger supervision of the AI ​​model.

[0558] The non-AI approach, also known as the legacy approach, refers to pausing or abandoning the initial information obtained based on the AI ​​model. In this scenario, the result of the AI ​​model's inference does not meet expectations, and the result can be discarded. It's understandable that the non-AI approach is relative to the approach of determining the initial information based on an AI model.

[0559] Adjustments to an AI model can include at least one of the following: model updates, model changes, model switching, model fine-tuning, changes to model input information, and changes to model output information.

[0560] Optionally, the triggering condition for the first operation includes at least one of the following:

[0561] After using the AI ​​model for inference for more than M hours, the first piece of information that meets the performance requirements has still not been obtained;

[0562] The AI ​​model failed to complete the AI ​​inference, or the AI ​​model successfully completed the AI ​​inference.

[0563] N AI inferences were performed using an AI model;

[0564] Where M and N are both positive integers and can be preset values.

[0565] In this embodiment, at least one of N and N can be predefined by the protocol or configured by the network-side device.

[0566] If the AI ​​model fails to obtain the first information that meets the performance requirements after inference time M, for example, the number of failures in full-duplex transmission based on the first information is greater than or equal to the preset number.

[0567] The AI ​​model failed to complete the AI ​​inference successfully. For example, the AI ​​model failed to perform inference or failed to obtain the first information.

[0568] Successfully complete AI inference using an AI model; for example, successfully obtain the first piece of information using an AI model.

[0569] In this embodiment, the first operation is performed when the triggering conditions are met, which helps to ensure that accurate transmission information is obtained.

[0570] In some optional embodiments, the metrics for AI model inference include at least one of the following:

[0571] The complexity of AI models;

[0572] Latency of AI model inference;

[0573] Success rate of AI model inference;

[0574] The reliability of the results output by the AI ​​model.

[0575] The complexity of AI models is defined with different complexity indicators for different types / capabilities of network-side devices, terminals, or servers. For example, for ordinary terminals, the complexity of the AI ​​models they use must not exceed the first value.

[0576] The latency of AI model inference can be understood as the duration of prediction, inference, or processing using the AI ​​model. Specifically, the duration of prediction, inference, or processing using the AI ​​model cannot exceed a first preset duration.

[0577] The success rate of AI model inference can be understood as the success rate of prediction, inference, or processing using the AI ​​model within a specific time period. For example, the success rate of AI model prediction can be the ratio of the number of successful predictions made using the AI ​​model within a specific time period to the total number of predictions made within that specific time period. Alternatively, the success rate of AI model prediction can be a value determined based on at least two success rates statistically analyzed over at least two specific time periods, such as the average of at least two success rates. The success rate statistically analyzed for each specific time period is the ratio of the number of successful predictions made using the AI ​​model within that specific time period to the total number of predictions made within that specific time period. Here, the specific time period can be a predefined duration by the protocol or a duration configured by the network-side device.

[0578] Specifically, the success rate of using AI models for prediction, reasoning, or processing must not be less than the second value.

[0579] The reliability of the results output by the AI ​​model, for example, the probability that the first piece of information inferred using the AI ​​model meets the performance requirements is greater than or equal to the third value.

[0580] For example, the first value, the second value, and the third value can be values ​​predefined by the protocol or values ​​configured for network-side devices.

[0581] It should be noted that the metrics for AI model inference can be used to determine whether the performance of AI model inference meets the metric requirements.

[0582] Optionally, the method further includes:

[0583] The first device trains at least a portion of the AI ​​model in the AI ​​model;

[0584] or,

[0585] The first device receives model information, which is used to determine at least a portion of the AI ​​model.

[0586] In one embodiment, at least a portion of the AI ​​model is trained by a first device. In this case, if the first device performs AI inference, it can perform inference based on the trained at least a portion of the AI ​​model; if the second device performs the AI ​​model, the first device can send the trained at least a portion of the AI ​​model or the identifier of the at least a portion of the AI ​​model to the second device.

[0587] In some optional embodiments, the first device may acquire at least some input information for AI model training sent by at least one device. For example, if the first device is a terminal, the first device may receive at least some input information sent by at least one of network-side devices, servers, and satellites, and train at least some AI models in the AI ​​model based on the received at least some input information.

[0588] In another embodiment, the first device can receive model information, for example, it can receive model information from the second device. The model information may include at least a portion of the AI ​​model or the identifier of at least a portion of the AI ​​model, and then the first device can perform inference based on at least a portion of the AI ​​model.

[0589] In some alternative embodiments, the first device may send at least some input information for training the AI ​​model to the second device, and the second device may train at least a portion of the AI ​​model based on the received at least some input information.

[0590] It is understandable that the parameters included in the input information used for AI model training and the parameters included in the input information used for AI model inference can be all the same or partially the same.

[0591] It should also be noted that AI model training can be performed before inference to obtain the AI ​​model; alternatively, it can be performed online to update the AI ​​model, thereby improving its accuracy and reliability. The AI ​​model training can be performed by a terminal, base station, TRP, core network equipment, or server, with no specific limitation. The server includes, but is not limited to, one of the following: OTT server, third-party service provider server, or internet server.

[0592] In some optional embodiments, the relevant information used for AI model training includes at least one of the following:

[0593] The input information used for AI model training includes at least the various parameter items of the input information used for AI model inference;

[0594] Labels, ground truth values, or model output information used for AI model training;

[0595] Loss function used for training AI models;

[0596] AI algorithms or AI algorithm indexes used for AI model training;

[0597] Reward information, adjustment information, or feedback information used for training AI models.

[0598] The reward information, adjustment information, or feedback information used for AI model training may include at least one of the following:

[0599] Whether a rollback occurs (i.e., acquiring full-duplex transmission resources using traditional methods);

[0600] The number of times rollbacks occurred;

[0601] The difference between the failure probability of full-duplex transmission in AI inference and the failure probability of actual full-duplex transmission.

[0602] The number of times AI inference failed.

[0603] Optionally, the triggering type for AI model training includes at least one of the following: conditional or event-triggered, periodic triggering, and semi-static triggering.

[0604] Optionally, the conditions or events that trigger AI model training include at least one of the following:

[0605] The timer used to trigger the training of the AI ​​model times out;

[0606] TAG-related timers timed out;

[0607] Received instruction information to guide AI training;

[0608] The terminal connects to the new cell.

[0609] The terminal switches frequencies or frequency bands;

[0610] Terminal switching to a different operator or Public Land Mobile Network (PLMN);

[0611] AI model inference failed;

[0612] The AI ​​model fails inference P times in a row, where P is a positive integer.

[0613] The number of inference failures by the AI ​​model has reached the fourth threshold.

[0614] AI models were used for reasoning;

[0615] The terminal moves to a new cell, tracking area, or geographical location;

[0616] The terminal's moving speed changes, or the change in the terminal's moving speed is greater than or equal to the fifth threshold;

[0617] 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 the sixth threshold;

[0618] The timer used for AI model training has expired after the first duration.

[0619] There were K instances of model supervision or S consecutive instances of model supervision, where K and S are both positive integers.

[0620] The external environment of the terminal has changed;

[0621] The terminal's moving speed is greater than or equal to the seventh threshold, or the terminal's acceleration is greater than or equal to the eighth threshold;

[0622] The terminal's position changes, or the change in the terminal's position is greater than or equal to the ninth threshold;

[0623] The terminal's movement parameters have changed;

[0624] The terminal's spatial information has changed or the terminal's spatial transmission filter has changed;

[0625] The network-side equipment is configured for full-duplex transmission.

[0626] The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold.

[0627] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to eleven thresholds, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[0628] The interference signal strength corresponding to full-duplex transmission is equal to or greater than the twelfth threshold.

[0629] The terminal performs cell or TRP handover;

[0630] The terminal performs cell or TRP reselection;

[0631] Business arrives;

[0632] Received instruction information for determining full-duplex transmission information based on an AI model.

[0633] In this embodiment, at least one of the fourth to twelfth thresholds is predefined by the protocol or indicated by the network-side device.

[0634] Upon receiving instruction information for AI training, for example, the base station sends instruction information for model training to the terminal via MAC CE command.

[0635] The change in the terminal's moving speed is greater than or equal to the fifth threshold, that is, the terminal's moving speed changes significantly or drops sharply in a short period of time, for example, from 250 km / h to 3 km / h.

[0636] When the external environment of the terminal changes, for example, information about the environmental changes can be obtained through sensing.

[0637] The terminal's movement parameters may include, but are not limited to, at least one of the terminal's movement speed, acceleration, and movement direction.

[0638] The terminal's airspace information may include, but is not limited to, at least one of the beam, TCI, and SSB selected by the terminal.

[0639] When a network-side device is configured with full-duplex transmission, for example, when a dedicated full-duplex transmission configuration is configured on the network-side device, AI model training is triggered; when a terminal performs full-duplex transmission based on this full-duplex transmission configuration, the AI ​​model is triggered to perform inference.

[0640] The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold, and for example, it may include at least one of the following:

[0641] The number of downlink signal reception failures in full-duplex transmission under one or a set of time-domain resources is greater than or equal to the tenth threshold 1;

[0642] The number of downlink signal reception failures in full-duplex transmission under one or a group of frequency domain resources is greater than or equal to the tenth threshold 2;

[0643] The number of downlink signal reception failures in full-duplex transmission under one or a group of TCI or beam is greater than or equal to the tenth threshold 3;

[0644] The number of downlink signal reception failures in full-duplex transmission under one or a group of uplink transmit powers is greater than or equal to the tenth threshold 4;

[0645] The number of downlink signal reception failures in full-duplex transmission under the signal strength of one or a group of cells is greater than or equal to the tenth threshold 5;

[0646] The number of downlink signal reception failures in full-duplex transmission under one or a group of interference signal strengths is greater than or equal to the tenth threshold 6;

[0647] The number of downlink signal reception failures in full-duplex transmission under one or a group of guard band resources is greater than or equal to the tenth threshold 7;

[0648] The number of failed attempts to switch between different transmission modes is greater than or equal to the tenth threshold of 8.

[0649] Among them, the tenth threshold 1 to the tenth threshold 8 can be at least partially the same or at least partially different.

[0650] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the eleventh threshold, and for example, may include at least one of the following:

[0651] The uplink transmit power of full-duplex transmission under one or a set of time-domain resources is greater than or equal to the eleventh threshold 1;

[0652] The uplink transmit power for full-duplex transmission under one or a set of frequency domain resources is greater than or equal to the eleventh threshold 2;

[0653] The uplink transmit power for full-duplex transmission under one or a group of TCI or beams is greater than or equal to the eleventh threshold 3;

[0654] The uplink transmit power for full-duplex transmission under the signal strength of one or a group of cells is greater than or equal to the eleventh threshold 4;

[0655] The uplink transmit power of full-duplex transmission under one or a group of interference signal strengths is greater than or equal to the eleventh threshold 5;

[0656] The uplink transmit power for full-duplex transmission under one or a group of guard band resources is greater than or equal to the eleventh threshold 6;

[0657] The difference between the transmit power and the maximum transmit power corresponding to full-duplex transmission is greater than or equal to the eleventh threshold 7.

[0658] Among them, the eleventh threshold 1 to the eleventh threshold 7 can be at least partially the same or at least partially different.

[0659] For full-duplex transmission to reach its maximum uplink transmit power, for example, it may include at least one of the following:

[0660] The uplink transmit power of full-duplex transmission under one or a set of time-domain resources reaches the corresponding maximum transmit power;

[0661] The uplink transmit power of full-duplex transmission under one or a group of frequency domain resources reaches the corresponding maximum transmit power;

[0662] The uplink transmit power of full-duplex transmission under one or a group of TCI or beams reaches the corresponding maximum transmit power;

[0663] Under the signal strength of one or a group of cells, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power;

[0664] Under the strength of one or a group of interference signals, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power.

[0665] Under one or a group of guard band resources, the uplink transmit power of full-duplex transmission reaches the corresponding maximum transmit power.

[0666] The interference signal strength corresponding to full-duplex transmission is greater than or equal to the twelfth threshold, and can, for example, include at least one of the following:

[0667] The interference signal strength for full-duplex transmission under one or a set of time-domain resources is greater than or equal to the twelfth threshold 1;

[0668] The interference signal strength for full-duplex transmission under one or a set of frequency domain resources is greater than or equal to the twelfth threshold 2;

[0669] The number of downlink signal reception failures in full-duplex transmission under one or a group of TCI or beam is greater than or equal to the twelfth threshold 3;

[0670] The interference signal strength in full-duplex transmission at one or a group of uplink transmit powers is greater than or equal to the twelfth threshold 4.

[0671] The interference signal strength of full-duplex transmission under the RSRP of one or a group of cell signal strengths is greater than or equal to the twelfth threshold 5;

[0672] The interference signal strength for full-duplex transmission under one or a group of protection band resources is greater than or equal to the twelfth threshold 6.

[0673] Among them, the twelfth threshold 1 to the twelfth threshold 6 can be at least partially the same or at least partially different.

[0674] Service arrival can include UL service or data arrival or DL ​​service or data arrival. In some alternative embodiments, it can be a specific type of service arrival, such as a service with high latency requirements or a service with high reliability requirements.

[0675] The terminal's location changes; for example, the terminal moves to a specific location, such as the cell edge; or the change in the terminal's location exceeds a corresponding threshold. The terminal's movement parameters may include at least one of the following: the terminal's movement speed, direction of movement, acceleration, etc. The terminal's movement parameters change; for example, the terminal's speed or acceleration exceeds a corresponding threshold.

[0676] The terminal's spatial information can include beam information, among other things. AI model training is triggered when the terminal's spatial information changes; for example, AI model training is triggered during beam failure recovery.

[0677] It should be noted that the triggering condition for AI model training can mean that AI training will definitely be triggered as long as at least one of the triggering conditions is met; or it can mean that AI training can be carried out as long as at least one of the triggering conditions is met. However, whether AI training is triggered specifically needs to be determined by further considering AI-related capabilities and other indications from the network side.

[0678] For example, if at least one of the triggering conditions is met, the training of the AI ​​model is immediately triggered; or if at least one of the triggering conditions is met, it indicates that training based on the AI ​​model can be enabled, but it is necessary to combine AI-related capabilities and other indications from the network side to determine whether to trigger it.

[0679] In some optional embodiments, AI model training is periodic, and the periodic configuration information includes at least one of the following:

[0680] The starting point for periodic model training; for example, after the terminal receives the network configuration information, it performs periodic model training.

[0681] The interval for periodic model training; for example, triggering at least one model training session every N time intervals;

[0682] The number of times the model is trained or the training duration within a cycle.

[0683] In some optional embodiments, AI model training is semi-statically triggered, and semi-static triggering includes at least one of the following:

[0684] The distribution and activation of semi-static configuration information are triggered based on specific conditions / events; the semi-static configuration information includes the starting point, period, and duration of model training.

[0685] Semi-static configuration information is configured via RRC, and semi-static training of the model is performed by activating / deactivating it via DCI or MAC-CE.

[0686] Optionally, the labels used for AI model training include at least one of the following:

[0687] First information, whether or not, is obtained that the performance requirements are met;

[0688] The number of initial pieces of information obtained;

[0689] The duration of AI model training;

[0690] Energy consumption for AI model training;

[0691] The terminal and the network node of the first cell transmit the required first information.

[0692] Labels used for AI model training can also be called ground truth or true values ​​used for AI model training.

[0693] The first piece of information that meets the performance requirements may, for example, include at least one of the following:

[0694] The success rate of full-duplex transmission based on the first information is greater than or equal to the first threshold.

[0695] The failure rate of full-duplex transmission based on the first information is lower than the second threshold.

[0696] The transmission power required for successful full-duplex transmission based on the first information is lower than the third threshold.

[0697] The number of transmissions required for successful full-duplex transmission based on the first information is less than the fourth threshold.

[0698] The residual interference in full-duplex transmission based on the first information is below the fifth threshold.

[0699] The signal-to-noise ratio for full-duplex transmission based on the first information is below the sixth threshold.

[0700] Residual interference can be understood as the residual interference after interference cancellation or suppression. The signal-to-noise ratio (SNR) of full-duplex transmission can be used to represent residual interference.

[0701] The training time of an AI model is considered complete if, for example, the training time is greater than or equal to the target time.

[0702] The terminal and the network nodes of the first cell transmit the required first information. 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, then the training is considered complete.

[0703] In some optional embodiments, the labels used for AI model training may also include at least one of the following:

[0704] At least one piece of spatial information;

[0705] At least one transmission mode;

[0706] At least one primary performance information;

[0707] At least one first transmission parameter;

[0708] At least one second transmission parameter;

[0709] Resources for at least one protective belt;

[0710] At least one parameter related to uplink transmit power;

[0711] At least one piece of interference information.

[0712] It should be noted that the labels used for AI model training can be obtained through methods such as terminal feedback or by measurement by network-side devices or terminals.

[0713] In some alternative embodiments, the entity performing AI model training may include at least one of the following:

[0714] 1) Terminal;

[0715] 2) Network-side equipment;

[0716] For example, network-side equipment includes at least one of a base station, a TRP, and core network equipment (such as core network equipment specifically used for model training).

[0717] Among them, the base station or TRP can be the base station or TRP where the terminal is currently camped, the terminal is currently accessing, the terminal target is being switched, or the terminal target is being reselected.

[0718] 3) Server;

[0719] The server can be a device specifically used for training or inference or providing AI-related information, or it can be a third-party server, or a device provided by an OTT service provider, third-party service provider, or the Internet.

[0720] In some optional embodiments, performing partial model training only on the terminal side, network side, or server side, or performing joint training on the terminal side, network side, and server side, may include at least one of the following:

[0721] 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 uses the information reported by the terminal side (i.e. the output information of the terminal model training) as one of the input contents of its own model training.

[0722] The network side sends at least a portion of the output information of the model training to the terminal or server side, and the terminal or server side uses the information sent by the network side (i.e. the output information of the network side model training) as one of the input contents for its own model training.

[0723] The model is trained offline on the terminal, network, or server side, and then fine-tuned on the actual network.

[0724] In some optional embodiments, when at least part of the training of the AI ​​model occurs on the network side or server side, after the AI ​​model training is completed, the network side or server side sends at least part of the trained AI model to the terminal.

[0725] In some optional embodiments, when at least part of the training of the AI ​​model occurs on the terminal side or the server side, there may be multiple sets of trained AI models on the terminal side or the server side. 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 models to use for AI inference.

[0726] The multiple AI models may differ in at least one of the following ways: differences in training datasets, differences in label information, differences in input information, and differences in inference output. Auxiliary information may include the identifiers (IDs) of the multiple AI models and the classification labels of the datasets.

[0727] Network-side instructions can be direct network instructions containing at least one of the following: the AI ​​model ID, the dataset ID, and data acquisition-related configuration information. The terminal or server can determine which AI model to use for model inference based on at least one of the received AI model ID, dataset ID, and data acquisition-related configuration information.

[0728] In some optional embodiments, the criteria for determining whether AI model training is complete include at least one of the following:

[0729] The loss function used for training the AI ​​model satisfies the first preset condition;

[0730] The AI ​​model has been trained up to the first preset number of times;

[0731] The AI ​​model has undergone a second preset number of fine-tuning iterations.

[0732] At least one label used for training an AI model must satisfy the corresponding threshold condition.

[0733] The loss function used for training the AI ​​model satisfies a first preset condition. For example, the loss function used for training the AI ​​model satisfies a predefined requirement indicator or value, such as the training error being less than a predefined threshold. The loss function can be at least one of the following: the mean squared error or normalized mean squared error between the predicted and the true values, or the mean absolute error between the predicted and the true values.

[0734] The model has been trained a predefined number of times;

[0735] The number of fine-tuning iterations reached the predetermined value;

[0736] At least one label used for AI model training satisfies a corresponding threshold condition, for example, at least one piece of information in the labels used for AI model training is greater than or equal to the corresponding threshold, or at least one piece of information in the labels used for AI model training is less than or equal to the corresponding threshold.

[0737] Understandably, when the inference environment differs significantly from the training environment, the performance of full-duplex transmission of the first information inferred from the AI ​​model will be very poor, meaning the inferred first information will be inaccurate. Therefore, it is necessary to supervise the actual inference performance determined by the first information from the AI ​​model and trigger a series of adjustment measures based on the supervision results to ensure the reliability of the AI ​​model.

[0738] Optionally, the method further includes:

[0739] The first device supervises the AI ​​model;

[0740] or,

[0741] The first device receives the model supervision results from the AI ​​model.

[0742] For example, the model supervision results may include at least one of the following: the error between the AI ​​model's predicted value and the actual value, and a communication system performance indicator. The communication system performance indicator may include at least one of the following: transmission latency, throughput, etc.

[0743] In one embodiment, the first device can supervise the AI ​​model, and then determine whether the AI ​​model needs to be updated or retrained, or whether the AI ​​model needs to be switched, based on the model supervision results.

[0744] In some optional embodiments, the first device may also send the model supervision results to the second device, so that the second device can determine whether the AI ​​model needs to be updated or retrained based on the model supervision results of the AI ​​model.

[0745] In another embodiment, the second device can perform AI model supervision and send the model supervision results to the first device, so that the first device can determine whether the AI ​​model needs to be updated or retrained, or whether the AI ​​model needs to be switched, based on the model supervision results.

[0746] In some optional embodiments, the labels for AI model supervision can be the same as those used for AI model training, or they can be labels specifically designed for AI model supervision. These labels can also be referred to as the ground truth or true values ​​for AI model supervision.

[0747] Optionally, the configuration information for AI model supervision includes at least one of the following:

[0748] AI models or AI model identifiers that require model supervision;

[0749] The cycle of model supervision;

[0750] The duration of model supervision;

[0751] Information related to the detection window in model supervision;

[0752] Triggering conditions for model supervision;

[0753] Metrics for model supervision;

[0754] Labels for model supervision.

[0755] Information related to the detection window for model supervision may include at least one of the following: the duration of the supervision window and the number of samples used for model supervision.

[0756] For example, a terminal, network-side device, or server can perform AI model supervision based on configuration information used for AI model supervision.

[0757] Optionally, the triggering conditions for AI model supervision include at least one of the following:

[0758] The results of AI model inference do not meet the accuracy requirements;

[0759] At least one metric of the AI ​​model's inference does not meet the requirements;

[0760] The metrics for model supervision do not meet the requirements;

[0761] Timer timeout used for AI model supervision;

[0762] The terminal switches cells, TRPs, or beams;

[0763] AI model inference failed;

[0764] The AI ​​model fails inference T times in a row, where T is a positive integer.

[0765] The AI ​​model has failed inference a preset number of times;

[0766] AI model inference was used;

[0767] The terminal moves to a new cell, tracking area, or geographical location;

[0768] The terminal's moving speed is greater than or equal to the thirteenth threshold, or the terminal's acceleration is greater than or equal to the fourteenth threshold;

[0769] The external environment in which the AI ​​model's inference device exists has changed.

[0770] At least one metric for AI model inference may include at least one of the following: AI model complexity, AI model inference latency, AI model inference success rate, and the reliability of AI model output.

[0771] The metrics for model supervision can include at least one of the following: the error between the AI ​​model's predicted values ​​and the actual values, and communication system performance metrics. Among these, communication system performance metrics can include at least one of the following: transmission latency, throughput, etc.

[0772] Optionally, the method further includes at least one of the following:

[0773] The first device sends information about its AI-related capabilities.

[0774] The first device determines the AI-related capabilities of the second device;

[0775] The AI-related capability information is used to indicate at least one of the following:

[0776] Possesses or lacks the ability to train an AI model for acquiring first information;

[0777] Whether or not they possess the ability to obtain primary information through AI models;

[0778] It may or may not have the ability to send first auxiliary information, which is used to obtain first information through an AI model;

[0779] It may or may not have the ability to send second auxiliary information, which is used to train an AI model to acquire the first information.

[0780] In one embodiment, the first device may send AI-related capability information of the first device to the second device. For example, if the AI-related capability information of the first device indicates that the first device has the ability to train an AI model for predicting first information, the second device may determine that the first device shall train the AI ​​model for predicting first information; if the AI-related capability information of the first device indicates that the first device does not have the ability to train an AI model for predicting first information, the second device may determine that the AI ​​model for predicting first information shall be trained.

[0781] In another embodiment, the first device can determine the AI-related capability information of the second device. For example, if the AI-related capability information of the second device indicates that the second device has the ability to train 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 will be performed by the second device; if the AI-related capability information of the second device indicates that the second device does not have the ability to train 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 will be performed.

[0782] Understandably, before terminals, network-side devices, or servers can train, supervise, or infer AI models, they need to define their relevant capabilities and provide methods for determining those capabilities. This helps each node flexibly implement its corresponding features and facilitates feature implementation between nodes.

[0783] Optionally, the first device determines the AI-related capability information of the second device, including:

[0784] The first device determines the AI-related capability information of the second device based on at least one of the following:

[0785] The equipment type of the second device;

[0786] AI-related capability information indicated by reference signals;

[0787] The control information sent by the second device carries AI-related capability information;

[0788] The AI-related capability information carried in the RRC signaling sent by the second device;

[0789] AI-related capability information carried in the interface messages between the first device and the second device.

[0790] 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 can be 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.).

[0791] For AI-related capability information indicated by reference signals, such as RACH resources or SRS resources, it indicates the ability to train or infer AI models.

[0792] Control information may include uplink control information or physical layer control information (e.g., uplink control information (UCI) reported by the terminal to the network).

[0793] The interface messages between the first device and the second device can be specific interface messages, which may be specific to a particular AI model or applicable to all AI models. For example, if one of the first and second devices is a terminal and the other is a network-side device, the interface messages between them can be interface messages between the terminal and the network-side device. If one of the first and second devices is a terminal and the other is a server, the interface messages between them can be interface messages between the terminal and the server. If one of the first and second devices is a network-side device and the other is a server, the interface messages between them can be interface messages between the network-side device and the server.

[0794] It is understandable that the second device can determine the AI-related capability information of the first device based on at least one of the following:

[0795] The equipment type of the first device;

[0796] AI-related capability information indicated by reference signals;

[0797] The control information sent by the first device carries AI-related capability information;

[0798] The AI-related capability information carried in the RRC signaling sent by the first device;

[0799] AI-related capability information carried in the interface messages between the first device and the second device.

[0800] In some alternative embodiments, if the terminal performs AI model training / inference, the type of terminal needs to be considered, as different types of terminals may have different AI model training / inference capabilities.

[0801] For example, the input information used for model training / inference differs depending on the type of terminal. For instance, less input information should be used for model training on less capable terminal devices.

[0802] For example, the labels used for model training differ for different types of terminals.

[0803] For example, the execution method of model training differs depending on the type of terminal. For instance, for terminal devices with weaker capabilities, model training can be performed only on the network side, or only a small part of the joint model training can be performed on the terminal side. For example, model training involving user privacy data can be performed on the terminal side.

[0804] For example, the AI ​​models used for training differ depending on the type of device. For instance, overly complex AI models may not be applicable to devices with limited capabilities.

[0805] In summary, the transmission method provided by the embodiments of this application can select full-duplex transmission mode or full-duplex transmission resources based on AI models, ensuring resource utilization. At the same time, it can reasonably utilize full-duplex transmission mode or full-duplex transmission resources to reduce terminal power consumption, ensure the performance of full-duplex transmission, and reduce transmission latency.

[0806] Please see Figure 7 , Figure 7 This is a flowchart of a transmission method provided in an embodiment of this application. This method can be executed by a second device, such as... Figure 7 As shown, it includes the following steps:

[0807] Step 701: The second device performs a second operation, which includes at least one of the following:

[0808] The first information is obtained based on the AI ​​model and sent to the first device.

[0809] Receive second information from the first device, the second information including at least one of the following: the first information, at least a portion of the input information of the AI ​​model;

[0810] Training at least a portion of the AI ​​model;

[0811] Send model information, which is used to identify at least a portion of the AI ​​model;

[0812] Send the supervision results of the AI ​​model;

[0813] Send an instruction message to trigger AI model training;

[0814] Send an instruction message to trigger AI model inference;

[0815] The AI ​​model is used to predict at least one of the following:

[0816] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0817] At least one piece of spatial information;

[0818] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0819] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[0820] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0821] Resources for at least one protective belt;

[0822] At least one parameter related to uplink transmit power;

[0823] At least one piece of interference information.

[0824] Optionally, the airspace information includes at least one of the following: airspace information corresponding to downlink transmission and airspace information corresponding to uplink transmission.

[0825] Optionally, the first performance information includes at least one of the following:

[0826] The probability of successful transmission in full-duplex mode;

[0827] The probability of transmission failure in full-duplex transmission mode;

[0828] The number of transmission failures in full-duplex transmission mode.

[0829] Optionally, the first information may also include at least one probability information;

[0830] Among them, the probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

[0831] Optionally, the input information for the AI ​​model includes at least one of the following:

[0832] Signal information, distance information, path loss information, secondary performance information, maximum uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side device status information, satellite status information, sensing information, non-terrestrial network NTN base station information, channel information, and time information; among which, the secondary performance information is the performance information related to transmission in full-duplex transmission mode.

[0833] Optionally, the signal information includes at least one of the following: signal strength information, signal quality information, and interference signal strength information.

[0834] Optionally, the signal strength information includes at least one of the following:

[0835] Uplink signal reception strength information between the first and second devices;

[0836] Downlink signal reception strength information between the first device and the second device;

[0837] or,

[0838] Signal quality information includes at least one of the following:

[0839] Signal quality information of the uplink signal between the first and second devices;

[0840] Signal quality information of the downlink signal between the first device and the second device;

[0841] or,

[0842] Interference signal strength information includes at least one of the following:

[0843] Self-interference intensity information of the first device;

[0844] Mutual interference strength information of the first device;

[0845] Self-interference intensity information of the second device;

[0846] Interference strength information of the second device.

[0847] Optionally, the distance information includes at least one of the following:

[0848] The distance between the first terminal and the network node of the first cell;

[0849] The distance between network nodes in the source cell and network nodes in the target cell;

[0850] The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell;

[0851] The distance between the first terminal and the second terminal;

[0852] or,

[0853] Path loss information includes at least one of the following:

[0854] Path loss between the first terminal and the network node of the first cell;

[0855] Path loss between network nodes in the source cell and network nodes in the target cell;

[0856] Path loss between network nodes of Pcell and network nodes of Scell;

[0857] 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.

[0858] Optionally, the second performance information includes at least one of the following:

[0859] The number of downlink signal reception failures in full-duplex transmission under specific time domain resources;

[0860] The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources;

[0861] The number of downlink signal reception failures in full-duplex transmission under specific spatial information;

[0862] The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power;

[0863] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[0864] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[0865] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

[0866] Optionally, business-related information includes at least one of the following:

[0867] Load status of at least one cell in the first cell;

[0868] Interference situation in at least one cell of the first cell;

[0869] The load status corresponding to at least one spatial feature of the first cell;

[0870] Interference situation corresponding to at least one spatial feature of the first cell;

[0871] The load status of at least one carrier or frequency point in the first cell;

[0872] Interference situation corresponding to at least one carrier and frequency point of the first cell;

[0873] 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.

[0874] 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.

[0875] or,

[0876] 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.

[0877] or,

[0878] The satellite's status information includes at least one of the following: the satellite's panel orientation, the satellite's speed, and the satellite's direction of movement.

[0879] Optionally, the method further includes:

[0880] The second device sends the first configuration information to the first device;

[0881] The first configuration information includes at least one of the following:

[0882] AI model or AI model identifier;

[0883] The application scope of AI model reasoning;

[0884] The inference cycle of AI models;

[0885] The effective duration of AI model inference;

[0886] Triggering conditions for AI model inference;

[0887] The configuration parameters of the AI ​​model include at least one of the following: the input information of the AI ​​model, the output information of the AI ​​model, the type of the input information of the AI ​​model, and the type of the output information of the AI ​​model.

[0888] The first instruction information is used to indicate whether joint reasoning is supported or required.

[0889] Optionally, the method further includes:

[0890] The second device sends a second instruction message to the first device. The second instruction message is used to indicate the activation or deactivation information of the AI ​​model.

[0891] Optionally, the triggering conditions for using AI models for reasoning include at least one of the following:

[0892] The timer used to trigger AI inference timed out;

[0893] Select transmission based on full-duplex transmission configuration;

[0894] The failure probability corresponding to full-duplex transmission is greater than or equal to the first threshold.

[0895] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[0896] The interference signal strength corresponding to full-duplex transmission is greater than or equal to the third threshold.

[0897] The terminal performs cell or TRP reselection;

[0898] The terminal performs cell or TRP handover;

[0899] Business arrives;

[0900] Received instruction information to perform AI inference;

[0901] The terminal's location has changed or the terminal's movement parameters have changed;

[0902] The terminal's spatial information has changed or the transmission filter has changed.

[0903] Optionally, the conditions or events that trigger AI model training include at least one of the following:

[0904] The timer used to trigger the training of the AI ​​model times out;

[0905] TAG-related timers timed out;

[0906] Received instruction information to guide AI training;

[0907] The terminal connects to the new cell.

[0908] The terminal switches frequencies or frequency bands;

[0909] Terminal switching to a different operator or public terrestrial mobile network (PLMN);

[0910] AI model inference failed;

[0911] The AI ​​model fails inference P times in a row, where P is a positive integer.

[0912] The number of inference failures by the AI ​​model has reached the fourth threshold.

[0913] AI models were used for reasoning;

[0914] The terminal moves to a new cell, tracking area, or geographical location;

[0915] The terminal's moving speed changes, or the change in the terminal's moving speed is greater than or equal to the fifth threshold;

[0916] 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 the sixth threshold;

[0917] The timer used for AI model training has expired after the first duration.

[0918] There were K instances of model supervision or S consecutive instances of model supervision, where K and S are both positive integers.

[0919] The external environment of the terminal has changed;

[0920] The terminal's moving speed is greater than or equal to the seventh threshold, or the terminal's acceleration is greater than or equal to the eighth threshold;

[0921] The terminal's position changes, or the change in the terminal's position is greater than or equal to the ninth threshold;

[0922] The terminal's movement parameters have changed;

[0923] The terminal's spatial information has changed or the terminal's spatial transmission filter has changed;

[0924] The network-side equipment is configured for full-duplex transmission.

[0925] The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold.

[0926] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to eleven thresholds, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[0927] The interference signal strength corresponding to full-duplex transmission is equal to or greater than the twelfth threshold.

[0928] The terminal performs cell or TRP handover;

[0929] The terminal performs cell or TRP reselection;

[0930] Business arrives;

[0931] Received instruction information for determining full-duplex transmission information based on an AI model.

[0932] Optionally, the labels used for AI model training include at least one of the following:

[0933] First information, whether or not, is obtained that the performance requirements are met;

[0934] The number of initial pieces of information obtained;

[0935] The duration of AI model training;

[0936] Energy consumption for AI model training;

[0937] The terminal and the network node of the first cell transmit the required first information.

[0938] Optionally, the configuration information for AI model supervision includes at least one of the following:

[0939] AI models or AI model identifiers that require model supervision;

[0940] The cycle of model supervision;

[0941] The duration of model supervision;

[0942] Information related to the detection window in model supervision;

[0943] Triggering conditions for model supervision;

[0944] Metrics for model supervision;

[0945] Labels for model supervision.

[0946] Optionally, the triggering conditions for AI model supervision include at least one of the following:

[0947] The results of AI model inference do not meet the accuracy requirements;

[0948] At least one metric of the AI ​​model's inference does not meet the requirements;

[0949] The metrics for model supervision do not meet the requirements;

[0950] Timer timeout used for AI model supervision;

[0951] The terminal switches cells, TRPs, or beams;

[0952] AI model inference failed;

[0953] The AI ​​model fails inference T times in a row, where T is a positive integer.

[0954] The AI ​​model has failed inference a third preset number of times;

[0955] AI model inference was used;

[0956] The terminal moves to a new cell, tracking area, or geographical location;

[0957] The terminal's moving speed is greater than or equal to the thirteenth threshold, or the terminal's acceleration is greater than or equal to the fourteenth threshold;

[0958] The external environment in which the AI ​​model's inference device exists has changed.

[0959] Optionally, the method further includes:

[0960] The second device receives AI-related capability information from the first device;

[0961] The AI-related capability information is used to indicate at least one of the following:

[0962] Possesses or lacks the ability to train an AI model for acquiring first information;

[0963] Whether or not they possess the ability to obtain primary information through AI models;

[0964] It may or may not have the ability to send first auxiliary information, which is used to obtain first information through an AI model;

[0965] It may or may not have the ability to send second auxiliary information, which is used to train an AI model to acquire the first information.

[0966] It should be noted that the implementation method of this method can be found in [reference needed]. Figure 6 The relevant descriptions of the embodiments shown are not repeated here.

[0967] It should be noted that the transmission method provided in this application embodiment can be executed by a transmission device. This application embodiment uses the execution of the transmission method by a transmission device as an example to illustrate the transmission device provided in this application embodiment.

[0968] This application provides a transmission device. As an example, the transmission device may be a communication device or a component within a communication device, such as a chip. The communication device may be a terminal, a network-side device, or a server, etc. Exemplarily, the terminal may include, but is not limited to, the type of terminal 11 listed, and the network-side device may include, but is not limited to, the type of network-side device 12 listed. This application does not impose specific limitations.

[0969] The transmission device includes a receiving module, a transmitting module, and a processing module. These modules can be implemented in software or hardware. When implemented in hardware, the processing module can be implemented by a processor. For example, the processor can include general-purpose processors, special-purpose processors, such as a Central Processing Unit (CPU), microprocessor, Digital Signal Processor (DSP), Artificial Intelligence (AI) processor, Graphics Processing Unit (GPU), Application Specific Integrated Circuit (ASIC), Network Processor (NP), Field Programmable Gate Array (FPGA), or other programmable logic devices, gate circuits, transistors, discrete hardware components, etc. The receiving and transmitting modules can be implemented by a communication interface, which can include one or more of the following: transceiver, pins, circuits, bus, radio frequency unit, etc.

[0970] For details, see Figure 8 When the transmission device is the first device or a component of the first device, the transmission device 800 includes: a processing module 801 for acquiring first information, the first information being information obtained based on an artificial intelligence (AI) model; and a transceiver module 802 for performing a 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.

[0971] The first piece of information includes at least one of the following:

[0972] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[0973] At least one piece of spatial information;

[0974] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[0975] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[0976] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[0977] Resources for at least one protective belt;

[0978] At least one parameter related to uplink transmit power;

[0979] At least one piece of interference information.

[0980] Optionally, the processing module is specifically used for:

[0981] Receive the first information from the second device;

[0982] or,

[0983] First information is obtained based on an AI model.

[0984] Optionally, the airspace information includes at least one of the following: airspace information corresponding to downlink transmission and airspace information corresponding to uplink transmission.

[0985] Optionally, the first performance information includes at least one of the following:

[0986] The probability of successful transmission in full-duplex mode;

[0987] The probability of transmission failure in full-duplex transmission mode;

[0988] The number of transmission failures in full-duplex transmission mode.

[0989] Optionally, the first transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions;

[0990] or,

[0991] The second transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions.

[0992] Optionally, the resources of the guard band include at least one of the following: the frequency domain location of the guard band, and the frequency domain size of the guard band.

[0993] Optionally, the relevant parameters of the uplink transmit power include at least one of the following: target uplink transmit power, target receive power value, maximum transmit power, power boost value, and power backoff value.

[0994] Optionally, the interference information includes at least one of the following: interference intensity information, interference signal information.

[0995] Optionally, the interference strength information includes at least one of the following: self-interference strength, mutual interference strength, and indication information used to indicate whether the interference strength meets the corresponding threshold.

[0996] Optionally, the interference signal information includes at least one of the following: at least one reverse signal of the transmitted signal, and at least one preprocessing information corresponding to the transmitted signal.

[0997] Optionally, the first information may also include at least one probability information;

[0998] Among them, the probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

[0999] Optionally, the input information for the AI ​​model includes at least one of the following:

[1000] Signal information, distance information, path loss information, secondary performance information, maximum uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side device status information, satellite status information, sensing information, non-terrestrial network NTN base station information, channel information, and time information; among which, the secondary performance information is the performance information related to transmission in full-duplex transmission mode.

[1001] Optionally, the signal information includes at least one of the following: signal strength information, signal quality information, and interference signal strength information.

[1002] Optionally, the signal strength information includes at least one of the following:

[1003] Uplink signal reception strength information between the first and second devices;

[1004] Downlink signal reception strength information between the first device and the second device;

[1005] or,

[1006] Signal quality information includes at least one of the following:

[1007] Signal quality information of the uplink signal between the first and second devices;

[1008] Signal quality information of the downlink signal between the first device and the second device;

[1009] or,

[1010] Interference signal strength information includes at least one of the following:

[1011] Self-interference intensity information of the first device;

[1012] Mutual interference strength information of the first device;

[1013] Self-interference intensity information of the second device;

[1014] Interference strength information of the second device.

[1015] Optionally, the distance information includes at least one of the following:

[1016] The distance between the first terminal and the network node of the first cell;

[1017] The distance between network nodes in the source cell and network nodes in the target cell;

[1018] The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell;

[1019] The distance between the first terminal and the second terminal;

[1020] or,

[1021] Path loss information includes at least one of the following:

[1022] Path loss between the first terminal and the network node of the first cell;

[1023] Path loss between network nodes in the source cell and network nodes in the target cell;

[1024] Path loss between network nodes of Pcell and network nodes of Scell;

[1025] 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.

[1026] Optionally, the second performance information includes at least one of the following:

[1027] The number of downlink signal reception failures in full-duplex transmission under specific time domain resources;

[1028] The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources;

[1029] The number of downlink signal reception failures in full-duplex transmission under specific spatial information;

[1030] The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power;

[1031] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[1032] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[1033] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

[1034] 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.

[1035] Optionally, business-related information includes at least one of the following:

[1036] Load status of at least one cell in the first cell;

[1037] Interference situation in at least one cell of the first cell;

[1038] The load status corresponding to at least one spatial feature of the first cell;

[1039] Interference situation corresponding to at least one spatial feature of the first cell;

[1040] The load status of at least one carrier or frequency point in the first cell;

[1041] Interference situation corresponding to at least one carrier and frequency point of the first cell;

[1042] 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.

[1043] 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.

[1044] or,

[1045] 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.

[1046] or,

[1047] The satellite's status information includes at least one of the following: the satellite's panel orientation, the satellite's speed, and the satellite's direction of movement.

[1048] Optionally, the processing module is also used for:

[1049] Obtain the first configuration information;

[1050] The first configuration information includes at least one of the following:

[1051] AI model or AI model identifier;

[1052] The application scope of AI model reasoning;

[1053] The inference cycle of AI models;

[1054] The effective duration of AI model inference;

[1055] Triggering conditions for AI model inference;

[1056] The configuration parameters of the AI ​​model include at least one of the following: the input information of the AI ​​model, the output information of the AI ​​model, the type of the input information of the AI ​​model, and the type of the output information of the AI ​​model.

[1057] The first instruction information is used to indicate whether joint reasoning is supported or required.

[1058] Optionally, the processing module is also used for:

[1059] Obtain the second instruction information, which is used to indicate the activation or deactivation information of the AI ​​model;

[1060] The first device activates or deactivates the AI ​​model based on the second instruction information.

[1061] Optionally, the triggering conditions for using AI models for reasoning include at least one of the following:

[1062] The timer used to trigger AI inference timed out;

[1063] Select transmission based on full-duplex transmission configuration;

[1064] The failure probability corresponding to full-duplex transmission is greater than or equal to the first threshold.

[1065] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[1066] The interference signal strength corresponding to full-duplex transmission is greater than or equal to the third threshold.

[1067] The terminal performs cell or TRP reselection;

[1068] The terminal performs cell or TRP handover;

[1069] Business arrives;

[1070] Received instruction information to perform AI inference;

[1071] The terminal's location has changed or the terminal's movement parameters have changed;

[1072] The terminal's spatial information has changed or the transmission filter has changed.

[1073] Optionally, the processing module is also used for:

[1074] Perform a first operation, which includes at least one of the following:

[1075] Send a second message, which includes at least one of the following: a first message, at least a portion of the input information of the AI ​​model, and the status information of the first device;

[1076] Revert to using a non-AI method to determine the initial information;

[1077] Trigger adjustments to the AI ​​model;

[1078] Trigger the training of the AI ​​model;

[1079] Trigger supervision of the AI ​​model.

[1080] Optionally, the triggering condition for the first operation includes at least one of the following:

[1081] After using the AI ​​model for inference for more than M hours, the first piece of information that meets the performance requirements has still not been obtained;

[1082] The AI ​​model failed to complete the AI ​​inference, or the AI ​​model successfully completed the AI ​​inference.

[1083] N AI inferences were performed using an AI model;

[1084] Where M and N are both positive integers.

[1085] Optionally, the processing module is also used to train at least a portion of the AI ​​model in the AI ​​model;

[1086] or,

[1087] The transceiver module is also used to receive model information, which is used to identify at least a portion of the AI ​​model.

[1088] Optionally, the conditions or events that trigger AI model training include at least one of the following:

[1089] The timer used to trigger the training of the AI ​​model times out;

[1090] TAG-related timers timed out;

[1091] Received instruction information to guide AI training;

[1092] The terminal connects to the new cell.

[1093] The terminal switches frequencies or frequency bands;

[1094] Terminal switching to a different operator or public terrestrial mobile network (PLMN);

[1095] AI model inference failed;

[1096] The AI ​​model fails inference P times in a row, where P is a positive integer.

[1097] The number of inference failures by the AI ​​model has reached the fourth threshold.

[1098] AI models were used for reasoning;

[1099] The terminal moves to a new cell, tracking area, or geographical location;

[1100] The terminal's moving speed changes, or the change in the terminal's moving speed is greater than or equal to the fifth threshold;

[1101] 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 the sixth threshold;

[1102] The timer used for AI model training has expired after the first duration.

[1103] There were K instances of model supervision or S consecutive instances of model supervision, where K and S are both positive integers.

[1104] The external environment of the terminal has changed;

[1105] The terminal's moving speed is greater than or equal to the seventh threshold, or the terminal's acceleration is greater than or equal to the eighth threshold;

[1106] The terminal's position changes, or the change in the terminal's position is greater than or equal to the ninth threshold;

[1107] The terminal's movement parameters have changed;

[1108] The terminal's spatial information has changed or the terminal's spatial transmission filter has changed;

[1109] The network-side equipment is configured for full-duplex transmission.

[1110] The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold.

[1111] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to eleven thresholds, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[1112] The interference signal strength corresponding to full-duplex transmission is equal to or greater than the twelfth threshold.

[1113] The terminal performs cell or TRP handover;

[1114] The terminal performs cell or TRP reselection;

[1115] Business arrives;

[1116] Received instruction information for determining full-duplex transmission information based on an AI model.

[1117] Optionally, the labels used for AI model training include at least one of the following:

[1118] First information, whether or not, is obtained that the performance requirements are met;

[1119] The number of initial pieces of information obtained;

[1120] The duration of AI model training;

[1121] Energy consumption for AI model training;

[1122] The terminal and the network node of the first cell transmit the required first information.

[1123] Optionally, the processing module is also used to supervise the AI ​​model;

[1124] or,

[1125] The transceiver module is also used to receive the model supervision results of the AI ​​model.

[1126] Optionally, the configuration information for AI model supervision includes at least one of the following:

[1127] AI models or AI model identifiers that require model supervision;

[1128] The cycle of model supervision;

[1129] The duration of model supervision;

[1130] Information related to the detection window in model supervision;

[1131] Triggering conditions for model supervision;

[1132] Metrics for model supervision;

[1133] Labels for model supervision.

[1134] Optionally, the triggering conditions for AI model supervision include at least one of the following:

[1135] The results of AI model inference do not meet the accuracy requirements;

[1136] At least one metric of the AI ​​model's inference does not meet the requirements;

[1137] The metrics for model supervision do not meet the requirements;

[1138] Timer timeout used for AI model supervision;

[1139] The terminal switches cells, TRPs, or beams;

[1140] AI model inference failed;

[1141] The AI ​​model fails inference T times in a row, where T is a positive integer.

[1142] The AI ​​model has failed inference a third preset number of times;

[1143] AI model inference was used;

[1144] The terminal moves to a new cell, tracking area, or geographical location;

[1145] The terminal's moving speed is greater than or equal to the thirteenth threshold, or the terminal's acceleration is greater than or equal to the fourteenth threshold;

[1146] The external environment in which the AI ​​model's inference device exists has changed.

[1147] Optionally, the transceiver module is also used to send AI-related capability information of the first device;

[1148] And / or,

[1149] The processing module is also used to determine the AI-related capabilities of the second device;

[1150] The AI-related capability information is used to indicate at least one of the following:

[1151] Possesses or lacks the ability to train an AI model for acquiring first information;

[1152] Whether or not they possess the ability to obtain primary information through AI models;

[1153] It may or may not have the ability to send first auxiliary information, which is used to obtain first information through an AI model;

[1154] It may or may not have the ability to send second auxiliary information, which is used to train an AI model to acquire the first information.

[1155] Optionally, the processing module is specifically used for:

[1156] The AI-related capabilities of the second device are determined based on at least one of the following:

[1157] The equipment type of the second device;

[1158] AI-related capability information indicated by reference signals;

[1159] The control information sent by the second device carries AI-related capability information;

[1160] The AI-related capability information carried in the RRC signaling sent by the second device;

[1161] AI-related capability information carried in the interface messages between the first device and the second device.

[1162] The transmission device provided in this application embodiment can achieve... Figure 6 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[1163] See Figure 9 When the transmission device is a network-side device or a component within a network-side device, the transmission device 900 includes a processing module 901 for performing a second operation, the second operation including at least one of the following:

[1164] The first information is obtained based on the AI ​​model and sent to the first device.

[1165] Receive second information from the first device, the second information including at least one of the following: the first information, at least a portion of the input information of the AI ​​model;

[1166] Training at least a portion of the AI ​​model;

[1167] Send model information, which is used to identify at least a portion of the AI ​​model;

[1168] Send the supervision results of the AI ​​model;

[1169] Send an instruction message to trigger AI model training;

[1170] Send an instruction message to trigger AI model inference;

[1171] The AI ​​model is used to predict at least one of the following:

[1172] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[1173] At least one piece of spatial information;

[1174] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[1175] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[1176] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[1177] Resources for at least one protective belt;

[1178] At least one parameter related to uplink transmit power;

[1179] At least one piece of interference information.

[1180] Optionally, the airspace information includes at least one of the following: airspace information corresponding to downlink transmission and airspace information corresponding to uplink transmission.

[1181] Optionally, the first performance information includes at least one of the following:

[1182] The probability of successful transmission in full-duplex mode;

[1183] The probability of transmission failure in full-duplex transmission mode;

[1184] The number of transmission failures in full-duplex transmission mode.

[1185] Optionally, the first information may also include at least one probability information;

[1186] Among them, the probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

[1187] Optionally, the input information for the AI ​​model includes at least one of the following:

[1188] Signal information, distance information, path loss information, secondary performance information, maximum uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side device status information, satellite status information, sensing information, non-terrestrial network NTN base station information, channel information, and time information; among which, the secondary performance information is the performance information related to transmission in full-duplex transmission mode.

[1189] Optionally, the signal information includes at least one of the following: signal strength information, signal quality information, and interference signal strength information.

[1190] Optionally, the signal strength information includes at least one of the following:

[1191] Uplink signal reception strength information between the first and second devices;

[1192] Downlink signal reception strength information between the first device and the second device;

[1193] or,

[1194] Signal quality information includes at least one of the following:

[1195] Signal quality information of the uplink signal between the first and second devices;

[1196] Signal quality information of the downlink signal between the first device and the second device;

[1197] or,

[1198] Interference signal strength information includes at least one of the following:

[1199] Self-interference intensity information of the first device;

[1200] Mutual interference strength information of the first device;

[1201] Self-interference intensity information of the second device;

[1202] Interference strength information of the second device.

[1203] Optionally, the distance information includes at least one of the following:

[1204] The distance between the first terminal and the network node of the first cell;

[1205] The distance between network nodes in the source cell and network nodes in the target cell;

[1206] The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell;

[1207] The distance between the first terminal and the second terminal;

[1208] or,

[1209] Path loss information includes at least one of the following:

[1210] Path loss between the first terminal and the network node of the first cell;

[1211] Path loss between network nodes in the source cell and network nodes in the target cell;

[1212] Path loss between network nodes of Pcell and network nodes of Scell;

[1213] 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.

[1214] Optionally, the second performance information includes at least one of the following:

[1215] The number of downlink signal reception failures in full-duplex transmission under specific time domain resources;

[1216] The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources;

[1217] The number of downlink signal reception failures in full-duplex transmission under specific spatial information;

[1218] The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power;

[1219] The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength;

[1220] The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength;

[1221] The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

[1222] Optionally, business-related information includes at least one of the following:

[1223] Load status of at least one cell in the first cell;

[1224] Interference situation in at least one cell of the first cell;

[1225] The load status corresponding to at least one spatial feature of the first cell;

[1226] Interference situation corresponding to at least one spatial feature of the first cell;

[1227] The load status of at least one carrier or frequency point in the first cell;

[1228] Interference situation corresponding to at least one carrier and frequency point of the first cell;

[1229] 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.

[1230] 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.

[1231] or,

[1232] 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.

[1233] or,

[1234] The satellite's status information includes at least one of the following: the satellite's panel orientation, the satellite's speed, and the satellite's direction of movement.

[1235] Optionally, the apparatus further includes a transmitting module for transmitting first configuration information to the first device;

[1236] The first configuration information includes at least one of the following:

[1237] AI model or AI model identifier;

[1238] The application scope of AI model reasoning;

[1239] The inference cycle of AI models;

[1240] The effective duration of AI model inference;

[1241] Triggering conditions for AI model inference;

[1242] The configuration parameters of the AI ​​model include at least one of the following: the input information of the AI ​​model, the output information of the AI ​​model, the type of the input information of the AI ​​model, and the type of the output information of the AI ​​model.

[1243] The first instruction information is used to indicate whether joint reasoning is supported or required.

[1244] Optionally, the device further includes a sending module for sending second indication information to the first device, the second indication information being used to indicate activation or deactivation information of the AI ​​model.

[1245] Optionally, the triggering conditions for using AI models for reasoning include at least one of the following:

[1246] The timer used to trigger AI inference timed out;

[1247] Select transmission based on full-duplex transmission configuration;

[1248] The failure probability corresponding to full-duplex transmission is greater than or equal to the first threshold.

[1249] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[1250] The interference signal strength corresponding to full-duplex transmission is greater than or equal to the third threshold.

[1251] The terminal performs cell or TRP reselection;

[1252] The terminal performs cell or TRP handover;

[1253] Business arrives;

[1254] Received instruction information to perform AI inference;

[1255] The terminal's location has changed or the terminal's movement parameters have changed;

[1256] The terminal's spatial information has changed or the transmission filter has changed.

[1257] Optionally, the conditions or events that trigger AI model training include at least one of the following:

[1258] The timer used to trigger the training of the AI ​​model times out;

[1259] TAG-related timers timed out;

[1260] Received instruction information to guide AI training;

[1261] The terminal connects to the new cell.

[1262] The terminal switches frequencies or frequency bands;

[1263] Terminal switching to a different operator or public terrestrial mobile network (PLMN);

[1264] AI model inference failed;

[1265] The AI ​​model fails inference P times in a row, where P is a positive integer.

[1266] The number of inference failures by the AI ​​model has reached the fourth threshold.

[1267] AI models were used for reasoning;

[1268] The terminal moves to a new cell, tracking area, or geographical location;

[1269] The terminal's moving speed changes, or the change in the terminal's moving speed is greater than or equal to the fifth threshold;

[1270] 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 the sixth threshold;

[1271] The timer used for AI model training has expired after the first duration.

[1272] There were K instances of model supervision or S consecutive instances of model supervision, where K and S are both positive integers.

[1273] The external environment of the terminal has changed;

[1274] The terminal's moving speed is greater than or equal to the seventh threshold, or the terminal's acceleration is greater than or equal to the eighth threshold;

[1275] The terminal's position changes, or the change in the terminal's position is greater than or equal to the ninth threshold;

[1276] The terminal's movement parameters have changed;

[1277] The terminal's spatial information has changed or the terminal's spatial transmission filter has changed;

[1278] The network-side equipment is configured for full-duplex transmission.

[1279] The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold.

[1280] The uplink transmit power corresponding to full-duplex transmission is greater than or equal to eleven thresholds, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power;

[1281] The interference signal strength corresponding to full-duplex transmission is equal to or greater than the twelfth threshold.

[1282] The terminal performs cell or TRP handover;

[1283] The terminal performs cell or TRP reselection;

[1284] Business arrives;

[1285] Received instruction information for determining full-duplex transmission information based on an AI model.

[1286] Optionally, the labels used for AI model training include at least one of the following:

[1287] First information, whether or not, is obtained that the performance requirements are met;

[1288] The number of initial pieces of information obtained;

[1289] The duration of AI model training;

[1290] Energy consumption for AI model training;

[1291] The terminal and the network node of the first cell transmit the required first information.

[1292] Optionally, the configuration information for AI model supervision includes at least one of the following:

[1293] AI models or AI model identifiers that require model supervision;

[1294] The cycle of model supervision;

[1295] The duration of model supervision;

[1296] Information related to the detection window in model supervision;

[1297] Triggering conditions for model supervision;

[1298] Metrics for model supervision;

[1299] Labels for model supervision.

[1300] Optionally, the triggering conditions for AI model supervision include at least one of the following:

[1301] The results of AI model inference do not meet the accuracy requirements;

[1302] At least one metric of the AI ​​model's inference does not meet the requirements;

[1303] The metrics for model supervision do not meet the requirements;

[1304] Timer timeout used for AI model supervision;

[1305] The terminal switches cells, TRPs, or beams;

[1306] AI model inference failed;

[1307] The AI ​​model fails inference T times in a row, where T is a positive integer.

[1308] The AI ​​model has failed inference a third preset number of times;

[1309] AI model inference was used;

[1310] The terminal moves to a new cell, tracking area, or geographical location;

[1311] The terminal's moving speed is greater than or equal to the thirteenth threshold, or the terminal's acceleration is greater than or equal to the fourteenth threshold;

[1312] The external environment in which the AI ​​model's inference device exists has changed.

[1313] Optionally, the device further includes a receiving module for receiving AI-related capability information of the first device;

[1314] The AI-related capability information is used to indicate at least one of the following:

[1315] Possesses or lacks the ability to train an AI model for acquiring first information;

[1316] Whether or not they possess the ability to obtain primary information through AI models;

[1317] It may or may not have the ability to send first auxiliary information, which is used to obtain first information through an AI model;

[1318] It may or may not have the ability to send second auxiliary information, which is used to train an AI model to acquire the first information.

[1319] The transmission device provided in this application embodiment can achieve... Figure 7 The various processes implemented in the method embodiments achieve the same technical effect, and will not be described again here to avoid repetition.

[1320] like Figure 10 As shown, this application embodiment also provides a communication device 1000, including a processor 1001 and a memory 1002. The memory 1002 stores a program or instructions that can run on the processor 1001. For example, when the communication device 1000 is a terminal, a network-side device, or a server, the program or instructions are executed by the processor 1001 to implement the various steps of the transmission method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[1321] This application embodiment also provides a terminal, including a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement, for example... Figure 6 or Figure 7The steps in the method embodiment shown are illustrated. This terminal embodiment corresponds to the terminal-side method embodiment; all implementation processes and methods of the method embodiment can be applied to this terminal embodiment and achieve the same technical effect. The terminal can be... Figure 8 or Figure 9 The transmission device shown. Specifically, Figure 11 A schematic diagram of the hardware structure of a terminal to implement an embodiment of this application.

[1322] The terminal 1100 includes, but is not limited to, at least some of the following components: radio frequency unit 1101, network module 1102, audio output unit 1103, input unit 1104, sensor 1105, display unit 1106, user input unit 1107, interface unit 1108, memory 1109, and processor 1110.

[1323] Those skilled in the art will understand that the terminal 1100 may also include a power supply (such as a battery) for supplying power to various components. The power supply may be logically connected to the processor 1110 through a power management system, thereby enabling functions such as managing charging, discharging, and power consumption through the power management system. Figure 11 The terminal structure shown does not constitute a limitation on the terminal. The terminal may include more or fewer components than shown, or combine certain components, or have different component arrangements, which will not be elaborated here.

[1324] It should be understood that, in this embodiment, the input unit 1104 may include a graphics processor 11041 and a microphone 11042. The graphics processor 11041 processes image data of still images or videos obtained by an image capture device (such as a camera) in video capture mode or image capture mode. The display unit 1106 may include a display panel 11061, which may be configured in the form of a liquid crystal display, an organic light-emitting diode, or the like. The user input unit 1107 includes at least one of a touch panel 11071 and other input devices 11072. The touch panel 11071 is also called a touch screen. The touch panel 11071 may include a touch detection device and a touch controller. Other input devices 11072 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be described in detail here.

[1325] In this embodiment, after receiving downlink data from the network-side device, the radio frequency unit 1101 can transmit it to the processor 1110 for processing; in addition, the radio frequency unit 1101 can send uplink data to the network-side device. Typically, the radio frequency unit 1101 includes, but is not limited to, antennas, amplifiers, transceivers, couplers, low-noise amplifiers, duplexers, etc.

[1326] The memory 1109 can be used to store software programs or instructions, as well as various data. The memory 1109 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, the memory 1109 may include volatile memory or non-volatile memory. The non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DRRAM). The memory 1109 in this embodiment includes, but is not limited to, these and any other suitable types of memory.

[1327] Processor 1110 may include one or more processing units; optionally, processor 1110 integrates an application processor and a modem processor, wherein the application processor mainly handles operations involving the operating system, user interface, and applications, and the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the modem processor may also not be integrated into processor 1110.

[1328] The processor 1110 is used to acquire first information, which is information obtained based on an artificial intelligence (AI) model; the radio frequency unit 1101 is used to perform a first transmission based on the first information, and the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode.

[1329] The first piece of information includes at least one of the following:

[1330] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[1331] At least one piece of spatial information;

[1332] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[1333] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[1334] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[1335] Resources for at least one protective belt;

[1336] At least one parameter related to uplink transmit power;

[1337] At least one piece of interference information;

[1338] or,

[1339] Processor 1110 is configured to perform a second operation, the second operation comprising at least one of the following:

[1340] The first information is obtained based on the AI ​​model and sent to the first device.

[1341] Receive second information from the first device, the second information including at least one of the following: the first information, at least a portion of the input information of the AI ​​model;

[1342] Training at least a portion of the AI ​​model;

[1343] Send model information, which is used to identify at least a portion of the AI ​​model;

[1344] Send the supervision results of the AI ​​model;

[1345] Send an instruction message to trigger AI model training;

[1346] Send an instruction message to trigger AI model inference;

[1347] The AI ​​model is used to predict at least one of the following:

[1348] The first transmission mode includes a half-duplex transmission mode or a full-duplex transmission mode.

[1349] At least one piece of spatial information;

[1350] At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode;

[1351] At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter of the uplink transmission;

[1352] At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission;

[1353] Resources for at least one protective belt;

[1354] At least one parameter related to uplink transmit power;

[1355] At least one piece of interference information.

[1356] It is understood that the implementation process of each implementation method mentioned in this embodiment can refer to the relevant description of the foregoing transmission method embodiment and achieve the same or corresponding technical effects. To avoid repetition, it will not be described again here.

[1357] This application embodiment also provides a network-side device, including a processor and a communication interface, wherein the communication interface and the processor are coupled, and the processor is used to run programs or instructions to implement, for example... Figure 6 or Figure 7 The steps of the method embodiment shown are illustrated. This network-side device embodiment corresponds to the network-side device method embodiment. All implementation processes and methods of the method embodiment can be applied to this network-side device embodiment and achieve the same technical effect.

[1358] Specifically, embodiments of this application also provide a network-side device, which can be... Figure 8 or Figure 9 The transmission device shown. (e.g.) Figure 12 As shown, the network-side device 1200 includes: an antenna 1201, a radio frequency (RF) device 1202, a baseband device 1203, a processor 1204, and a memory 1205. The antenna 1201 is connected to the RF device 1202. In the uplink direction, the RF device 1202 receives information through the antenna 1201 and transmits the received information to the baseband device 1203 for processing. In the downlink direction, the baseband device 1203 processes the information to be transmitted and sends it to the RF device 1202. The RF device 1202 processes the received information and transmits it through the antenna 1201.

[1359] The method executed by the network-side device in the above embodiments can be implemented in the baseband device 1203, which includes a baseband processor.

[1360] The baseband device 1203 may include, for example, at least one baseband board on which multiple chips are disposed, such as... Figure 12As shown, one of the chips is, for example, a baseband processor, which is connected to the memory 1205 via a bus interface to call the program in the memory 1205 and execute the network device operation shown in the above method embodiment.

[1361] The network-side device may also include a network interface 1206, such as a Common Public Radio Interface (CPRI).

[1362] Specifically, the network-side device 1200 in this application embodiment further includes: instructions or programs stored in memory 1205 and executable on processor 1204, wherein processor 1204 calls the instructions or programs in memory 1205 to execute. Figure 8 or Figure 9 The methods executed by each module shown achieve the same technical effect, and to avoid repetition, they will not be described in detail here.

[1363] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the transmission method embodiment and achieve the same technical effect. To avoid repetition, they will not be described again here.

[1364] The processor in this embodiment refers to the processor in the terminal. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk. In some examples, the readable storage medium may be a non-transient readable storage medium.

[1365] This application also provides a chip, which 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 the various processes of the transmission method embodiment and achieve the same technical effect. To avoid repetition, it will not be described again here.

[1366] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[1367] This application also provides a computer program / program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the transmission method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[1368] This application also provides a wireless communication system, including a first device and a second device, wherein the first device can be used to perform the steps of the above transmission method, and the second device can be used to perform the steps of the above transmission method.

[1369] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[1370] From the above description of the embodiments, those skilled in the art can clearly understand that the methods of the embodiments can be implemented by means of a computer software product plus the necessary general-purpose hardware platform, and of course, they can also be implemented by hardware. The computer software product is stored in a storage medium (such as ROM, RAM, magnetic disk, optical disk, etc.) and includes several instructions to cause a terminal or network-side device to execute the methods of the various embodiments of this application.

[1371] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments. The specific embodiments are merely illustrative and not restrictive. Those skilled in the art can make many different embodiments under the guidance of this application without departing from the spirit and scope of the claims. All such embodiments are within the protection scope of this application.

Claims

1. A transmission method, characterized in that, include: The first device acquires first information, which is information obtained based on an artificial intelligence (AI) model. The first device performs a first transmission based on the first information, and the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode. 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 information; At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode; At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission; At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission; Resources for at least one protective zone; At least one parameter related to uplink transmit power; At least one piece of interference information.

2. The method according to claim 1, characterized in that, The first device acquires first information, including: The first device receives the first information from the second device; or, The first device obtains the first information based on the AI ​​model.

3. The method according to claim 1 or 2, characterized in that, The airspace information includes at least one of the following: airspace information corresponding to downlink transmission and airspace information corresponding to uplink transmission.

4. The method according to any one of claims 1 to 3, characterized in that, The first performance information includes at least one of the following: The probability of successful transmission in full-duplex mode; The probability of transmission failure in full-duplex transmission mode; The number of transmission failures in full-duplex transmission mode.

5. The method according to any one of claims 1 to 4, characterized in that, The first transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions; or, The second transmission parameter includes at least one of the following: time domain resources, frequency domain resources, spatial domain resources, number of transmissions, and number of retransmissions.

6. The method according to any one of claims 1 to 5, characterized in that, The resources of the guard band include at least one of the following: the frequency domain location of the guard band, and the frequency domain size of the guard band.

7. The method according to any one of claims 1 to 6, characterized in that, The relevant parameters of the uplink transmit power include at least one of the following: target uplink transmit power, target receive power value, maximum transmit power, power boost value, and power fallback value.

8. The method according to any one of claims 1 to 7, characterized in that, The interference information includes at least one of the following: interference intensity information, interference signal information.

9. The method according to claim 8, characterized in that, The interference strength information includes at least one of the following: self-interference strength, mutual interference strength, and indication information used to indicate whether the interference strength meets the corresponding threshold.

10. The method according to claim 8 or 9, characterized in that, The interference signal information includes at least one of the following: at least one reverse signal of the transmitted signal, and at least one preprocessing information corresponding to the transmitted signal.

11. The method according to any one of claims 1 to 10, characterized in that, The first information also includes at least one probability information; The probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

12. The method according to any one of claims 1 to 11, characterized in that, 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 uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side device status information, satellite status information, sensing 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 full-duplex transmission mode.

13. The method according to claim 12, characterized in that, The signal information includes at least one of the following: signal strength information, signal quality information, and interference signal strength information.

14. The method according to claim 13, characterized in that, The signal strength information includes at least one of the following: The received strength information of the uplink signal between the first device and the second device; The received strength information of the downlink signal between the first device and the second device; or, The signal quality information includes at least one of the following: Signal quality information of the uplink signal between the first device and the second device; Signal quality information of the downlink signal between the first device and the second device; or, The interference signal strength information includes at least one of the following: The self-interference intensity information of the first device; Interference strength information of the first device; Self-interference intensity information of the second device; Interference intensity information of the second device.

15. The method according to any one of claims 12 to 14, characterized in that, The distance information includes at least one of the following: The distance between the first terminal and the network node of the first cell; The distance between network nodes in the source cell and network nodes in the target cell; The distance between network nodes of the primary cell Pcell and network nodes of the secondary cell Scell; The distance between the first terminal and the second terminal; or, The path loss information includes at least one of the following: Path loss between the first terminal and the network node of the first cell; Path loss between network nodes in the source cell and network nodes in the target cell; Path loss between network nodes of Pcell and network nodes of Scell; 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.

16. The method according to any one of claims 12 to 15, characterized in that, The second performance information includes at least one of the following: The number of downlink signal reception failures in full-duplex transmission under specific time domain resources; The number of downlink signal reception failures in full-duplex transmission under specific frequency domain resources; The number of downlink signal reception failures in full-duplex transmission under specific spatial information; The number of downlink signal reception failures in full-duplex transmission at a specific uplink transmit power; The number of downlink signal reception failures in full-duplex transmission under specific cell signal strength; The number of downlink signal reception failures in full-duplex transmission under a specific interference signal strength; The number of downlink signal reception failures in full-duplex transmission under specific guard band resources.

17. The method according to any one of claims 12 to 16, characterized in that, 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.

18. The method according to any one of claims 12 to 17, characterized in that, The business-related information includes at least one of the following: Load status of at least one cell in the first cell; Interference situation in at least one cell of the first cell; The load status corresponding to at least one spatial feature of the first cell; Interference situation corresponding to at least one spatial feature of the first cell; The load status of at least one carrier or frequency point in the first cell; Interference situation corresponding to at least one carrier and frequency point of the first cell; 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.

19. The method according to any one of claims 12 to 18, characterized in that, 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 operator information supported by the terminal, the network type information supported by the terminal, the terminal's panel orientation information, the terminal's type, the terminal's network scenario information, and the environment information in which the terminal is located. or, 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. or, The satellite's status information includes at least one of the following: the satellite's panel orientation, the satellite's moving speed, and the satellite's moving direction.

20. The method according to any one of claims 1 to 19, characterized in that, The method further includes: The first device acquires the first configuration information; The first configuration information includes at least one of the following: AI model or AI model identifier; The application scope of AI model reasoning; The inference cycle of AI models; The effective duration of AI model inference; Triggering conditions for AI model inference; The configuration parameters of the AI ​​model include at least one of the following: the input information of the AI ​​model, the output information of the AI ​​model, the type of the input information of the AI ​​model, and the type of the output information of the AI ​​model. The first instruction information is used to indicate whether joint reasoning is supported or required.

21. The method according to any one of claims 1 to 20, characterized in that, The method further includes: The first device acquires second indication information, which is used to indicate the activation or deactivation information of the AI ​​model; The first device activates or deactivates the AI ​​model according to the second instruction information.

22. The method according to any one of claims 1 to 21, characterized in that, The triggering conditions for using the AI ​​model for reasoning include at least one of the following: The timer used to trigger AI inference timed out; Select transmission based on full-duplex transmission configuration; The failure probability corresponding to full-duplex transmission is greater than or equal to the first threshold. The uplink transmit power corresponding to full-duplex transmission is greater than or equal to the second threshold, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power; The interference signal strength corresponding to full-duplex transmission is greater than or equal to the third threshold. The terminal performs cell or TRP reselection; The terminal performs cell or TRP handover; Business arrives; Received instruction information to perform AI inference; The terminal's location has changed or the terminal's movement parameters have changed; The terminal's spatial information has changed or the transmission filter has changed.

23. The method according to any one of claims 1 to 22, characterized in that, The method further includes: The first device trains at least a portion of the AI ​​models in the AI ​​model; or, The first device receives model information, which is used to determine at least a portion of the AI ​​model.

24. The method according to claim 23, characterized in that, The conditions or events that trigger the training of the AI ​​model include at least one of the following: The timer used to trigger the training of the AI ​​model times out; TAG-related timers timed out; Received instruction information to guide AI training; The terminal connects to the new cell; The terminal switches frequencies or frequency bands; Terminal switching to a different operator or public terrestrial mobile network (PLMN); AI model inference failed; The AI ​​model fails inference P times in a row, where P is a positive integer. The number of inference failures by the AI ​​model has reached the fourth threshold. The AI ​​model was used for inference; The terminal moves to a new cell, tracking area, or geographical location; The terminal's moving speed changes, or the change in the terminal's moving speed is greater than or equal to the 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 the sixth threshold; The timer used for AI model training has expired after the first duration. There were K instances of model supervision or S consecutive instances of model supervision, where K and S are both positive integers. The external environment of the terminal has changed; The terminal's moving speed is greater than or equal to the seventh threshold, or the terminal's acceleration is greater than or equal to the eighth threshold; The terminal's position changes, or the change in the terminal's position is greater than or equal to the ninth threshold; The terminal's movement parameters have changed; The terminal's spatial information has changed or the terminal's spatial transmission filter has changed; The network-side equipment is configured for full-duplex transmission. The failure probability corresponding to full-duplex transmission is greater than or equal to the tenth threshold. The uplink transmit power corresponding to full-duplex transmission is greater than or equal to eleven thresholds, or the uplink transmit power corresponding to full-duplex transmission reaches the maximum transmit power; The interference signal strength corresponding to full-duplex transmission is equal to or greater than the twelfth threshold. The terminal performs cell or TRP handover; The terminal performs cell or TRP reselection; Business arrives; Received instruction information for determining full-duplex transmission information based on an AI model.

25. The method according to claim 23 or 24, characterized in that, The labels used for training the AI ​​model include at least one of the following: First information, whether or not, is obtained that the performance requirements are met; The number of initial pieces of information obtained; The duration of AI model training; Energy consumption for AI model training; The terminal and the network node of the first cell transmit the required first information.

26. The method according to any one of claims 1 to 25, characterized in that, The method further includes: The first device supervises the AI ​​model; or, The first device receives the model supervision results of the AI ​​model.

27. The method according to claim 26, characterized in that, The configuration information used for supervising the AI ​​model includes at least one of the following: AI models or AI model identifiers that require model supervision; The cycle of model supervision; The duration of model supervision; Information related to the detection window in model supervision; Triggering conditions for model supervision; Metrics for model supervision; Labels for model supervision.

28. The method according to claim 26 or 27, characterized in that, The triggering conditions for AI model supervision include at least one of the following: The results of the AI ​​model's inference do not meet the accuracy requirements; At least one metric of the AI ​​model's inference does not meet the requirements; The metrics for model supervision do not meet the requirements; The timer used for supervising the AI ​​model timed out; The terminal switches cells, TRPs, or beams; The AI ​​model inference failed. The AI ​​model fails inference T times consecutively, where T is a positive integer. The AI ​​model's inference failure count reached the third preset number; The AI ​​model was used for inference; The terminal moves to a new cell, tracking area, or geographical location; The terminal's moving speed is greater than or equal to the thirteenth threshold, or the terminal's acceleration is greater than or equal to the fourteenth threshold; The external environment in which the AI ​​model's inference device exists has changed.

29. The method according to any one of claims 1 to 28, characterized in that, The method further includes at least one of the following: The first device sends information about its AI-related capabilities. The first device determines the AI-related capability information of the second device; The AI-related capability information is used to indicate at least one of the following: Possesses or lacks the ability to train an AI model for acquiring first information; Whether or not they possess the ability to obtain primary information through AI models; It may or may not have the ability to send first auxiliary information, which is used to obtain first information through an AI model; It may or may not have the ability to send second auxiliary information, which is used to train an AI model for acquiring the first information.

30. A transmission method, characterized in that, include: The second device performs a second operation, the second operation including at least one of the following: The first information is obtained based on the AI ​​model, and the first information is sent to the first device; Receive second information from the first device, the second information including at least one of the following: first information, at least a portion of the input information of the AI ​​model; Training at least a portion of the AI ​​model; Send model information, which is used to identify at least a portion of the AI ​​model; Send the supervision results of the AI ​​model; Send an instruction message to trigger AI model training; Send an instruction message to trigger 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 spatial information; At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode; At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission; At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission; Resources for at least one protective zone; At least one parameter related to uplink transmit power; At least one piece of interference information.

31. The method according to claim 30, characterized in that, The first information also includes at least one probability information; The probability information corresponds to at least one of the following: at least one spatial information, at least one transmission mode, at least one first transmission parameter, at least one second transmission parameter, at least one guard band resource, and at least one uplink transmit power related parameter.

32. The method according to claim 30 or 31, characterized in that, 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 uplink transmit power, area information, frequency domain information, beam information, delay information, service-related information, terminal status information, network-side device status information, satellite status information, sensing 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 full-duplex transmission mode.

33. A transmission device, characterized in that, include: The processing module is used to acquire first information, which is information obtained based on an artificial intelligence (AI) model. The transceiver module is also used to perform a first transmission based on the first information, wherein the transmission mode corresponding to the first transmission is a half-duplex transmission mode or a full-duplex transmission mode. 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 information; At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode; At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission; At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission; Resources for at least one protective zone; At least one parameter related to uplink transmit power; At least one piece of interference information.

34. A transmission device, characterized in that, include: A processing module is configured to perform a second operation, the second operation including at least one of the following: The first information is obtained based on the AI ​​model, and the first information is sent to the first device; Receive second information from the first device, the second information including at least one of the following: first information, at least a portion of the input information of the AI ​​model; Training at least a portion of the AI ​​model; Send model information, which is used to identify at least a portion of the AI ​​model; Send the supervision results of the AI ​​model; Send an instruction message to trigger AI model training; Send an instruction message to trigger 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 spatial information; At least one first performance information, wherein the first performance information is performance information related to transmission in full-duplex transmission mode; At least one first transmission parameter, wherein the first transmission parameter is the transmission parameter for uplink transmission; At least one second transmission parameter, wherein the second transmission parameter is a transmission parameter for downlink transmission; Resources for at least one protective zone; At least one parameter related to uplink transmit power; At least one piece of interference information.

35. A first device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the transmission method as described in any one of claims 1 to 29.

36. A second device, characterized in that, It includes a processor and a memory, the memory storing a program or instructions that can run on the processor, the program or instructions being executed by the processor to implement the steps of the transmission method as described in any one of claims 30 to 32.

37. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the transmission method as described in any one of claims 1 to 29, or implement the steps of the transmission method as described in any one of claims 30 to 32.

38. A computer program product, characterized in that, The computer program product is executed by at least one processor to implement the steps of the transmission method as claimed in any one of claims 1 to 29, or to implement the steps of the transmission method as claimed in any one of claims 30 to 32.

Images