WO2026007673A1 - 一种通信方法及装置 - Google Patents

一种通信方法及装置

Info

Publication number
WO2026007673A1
WO2026007673A1 PCT/CN2025/100961 CN2025100961W WO2026007673A1 WO 2026007673 A1 WO2026007673 A1 WO 2026007673A1 CN 2025100961 W CN2025100961 W CN 2025100961W WO 2026007673 A1 WO2026007673 A1 WO 2026007673A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
network
target model
candidate
model
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/100961
Other languages
English (en)
French (fr)
Inventor
庞旭
秦志金
黄印桓
杨定熹
徐瑞
秦熠
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tsinghua University
Huawei Technologies Co Ltd
Original Assignee
Tsinghua University
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tsinghua University, Huawei Technologies Co Ltd filed Critical Tsinghua University
Publication of WO2026007673A1 publication Critical patent/WO2026007673A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • This application relates to the field of wireless communication technology, and in particular to a communication method and apparatus.
  • Semantic communication refers to the technology of encoding raw data (including selective feature extraction and compression) and then transmitting the encoded data to achieve communication using semantically represented information.
  • This application provides a communication method and apparatus for optimizing communication quality.
  • this application provides a communication method applied to a first device, which is a data transmitting device.
  • the first device can be a network device, such as an application server on the network side, a module (e.g., a circuit, chip, or chip system) within the application server, or a logical node, logical module, or software capable of implementing all or part of the application server's functions.
  • the first device can also be a terminal device, or a chip, unit, or module within a terminal device, or a communication device with terminal functions, or a chip, unit, or module within a communication device with terminal functions.
  • the first device sends first information to a second device, wherein the first information indicates a candidate model; then, the first device receives second information from the second device, wherein the second information indicates a target model, which is one of the candidate models, and the second device is a network device; finally, the first device encodes the first data according to the target model to obtain second data, and sends the second data to a third device, which is a data receiving device.
  • the first device can send candidate models to the second device before encoding the data to be transmitted (i.e., the first data), so that the second device can select a suitable target model from the candidate models and indicate the target model through second information.
  • the first device can use the target model to encode the first data, making the second data obtained after encoding the first data suitable for transmission by the second device, thereby optimizing communication quality.
  • candidate models are associated with network states, and at least two candidate models are associated with different network states, while the target model is associated with the current network state.
  • candidate models are associated with different network states, so that after determining the current network state, the second device can select a target model from the candidate models that is associated with the current network state, and indicate the target model through second information.
  • the first device can use the target model to encode the first data, making the second data obtained after encoding the first data suitable for transmission under the current network state, thereby optimizing communication quality.
  • the candidate models include at least two candidate models associated with the same network state, and the first information also indicates the priority of the at least two candidate models.
  • any network state can be associated with at least two candidate models. These at least two candidate models are marked with priorities to indicate the quality of the encoding of the first data by the at least two candidate models, so as to achieve the best selection and optimize the communication quality.
  • the second information further indicates the effective time of the target model; the encoding of the first data according to the target model includes: encoding the first data according to the target model within the effective time.
  • the target model is made available only in the current time period through the effective time, preventing the target model from being incompatible with the changed network status and ensuring the accuracy of the target model's use.
  • the effective time includes a start time
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model upon reaching the start time; or, the effective time includes a start time and an effective duration
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model upon reaching the start time and within the effective duration; or, the effective time includes a start time and an end time
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model during the period from the start time to the end time.
  • the method before sending the first information to the second device, the method further includes: determining the candidate model based on the attributes of the first data, wherein the attributes of the first data include at least one of the following: data volume, frame rate, and application scenario.
  • the candidate model is associated with the first data, so that the second data can be better adapted to transmission under the current network conditions, thereby optimizing communication quality.
  • the first device is an application server
  • the second device is a network device
  • the third device is a terminal device, wherein the network device is a core network device or an access network device; or, the first device is a terminal device, the second device is a network device, and the third device is a terminal device, wherein the network device is a core network device or an access network device; or, the first device is an application server, the second device is a routing device, and the third device is a terminal device.
  • the first data is video data
  • the candidate model is a model used to encode the video data
  • this application provides a communication method that can be applied to a second device, which is a network device, such as an access network device, a module (e.g., a circuit, chip, or chip system) within an access network device, or a logical node, logical module, or software capable of implementing all or part of the functions of an access network device.
  • the second device can be a core network device, a module (e.g., a circuit, chip, or chip system) within a core network device, or a logical node, logical module, or software capable of implementing all or part of the functions of a core network device.
  • the second device receives first information from a first device, wherein the first information indicates a candidate model used for data encoding; then, it sends second information to the first device, wherein the second information indicates a target model, which is one of the candidate models.
  • the second device can select a target model from the candidate models and indicate the target model through the second information.
  • the first device can then use this target model to encode the first data, making the second data suitable for transmission by the second device, thereby optimizing communication quality.
  • the candidate models are associated with network states, wherein at least two candidate models are associated with different network states; based on this, the second device selects a target model from the candidate models according to the current network state.
  • selecting a target model from the candidate models based on the current network state includes: selecting at least two candidate models associated with the current network state from the candidate models, and then determining the target model from the at least two candidate models based on their priorities.
  • the second device can select a target model from the candidate models according to the current network status, so that the first device uses the target model to encode the first data, making the second data suitable for transmission under the current network status, thereby optimizing the communication quality.
  • the first information also indicates the priority of at least two candidate models.
  • the second information also indicates the effective time of the target model.
  • the effective time includes a start time; or, the effective time includes a start time and an effective duration; or, the effective time includes a start time and an end time.
  • One possible implementation further includes: receiving second data from the first device and sending the second data to a third device, wherein the second data is obtained by the first device encoding the first data according to the target model.
  • the first device is an application server and the second device is a network device, wherein the network device is a core network device or an access network device; or, the first device is a terminal device and the second device is a network device, wherein the network device is a core network device or an access network device; or, the first device is an application server and the second device is a routing device.
  • this application provides a communication method applied to a first device.
  • the first device receives third information sent from a second device, wherein the third information indicates the current network state; then, the first device selects a target model associated with the current network state from candidate models based on the current network state, wherein the candidate models are associated with the network state, and at least two candidate models are associated with different network states; furthermore, the first device encodes first data according to the target model to obtain second data, and sends the second data to a third device, wherein the third device is a data receiving device.
  • the third information further indicates the effective time of the target model; the encoding of the first data according to the target model includes: encoding the first data according to the target model within the effective time.
  • the effective time includes a start time
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model upon reaching the start time; or, the effective time includes a start time and an effective duration
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model upon reaching the start time and within the effective duration; or, the effective time includes a start time and an end time
  • encoding the first data according to the target model within the effective time includes: encoding the first data according to the target model during the period from the start time to the end time.
  • the method before determining the target model associated with the current network state from the candidate models of the current network state, the method further includes: determining the candidate model based on the attributes of the first data, wherein the attributes of the first data include at least one of the following: data volume, frame rate, and application scenario.
  • the first device is an application server
  • the second device is a network device
  • the third device is a terminal device, wherein the network device is a core network device or an access network device; or, the first device is a terminal device, the second device is a network device, and the third device is a terminal device, wherein the network device is a core network device or an access network device; or, the first device is an application server, the second device is a routing device, and the third device is a terminal device.
  • the first data is video data
  • the candidate model is a model used to encode the video data
  • this application provides a communication method applicable to a second device.
  • the second device sends third information to a first device, wherein the third information indicates the current network state; then, the second device receives second data from the first device and sends the second data to a third device, wherein the second data is obtained by the first device encoding first data according to a target model associated with the current network state.
  • the second device periodically sends the third information to the first device.
  • this application provides a communication device that has the functions of the first and third aspects described above.
  • the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.
  • this application provides a communication device that has the functions of the second and fourth aspects mentioned above.
  • the communication device includes modules, units, or means that perform the operations involved in the second aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.
  • this application provides a communication device including an interface circuit and one or more processors.
  • the one or more processors are coupled to a memory.
  • the memory stores part or all of the necessary computer programs or instructions for implementing the functions described in the first to fourth aspects.
  • the one or more processors are executable to carry out the computer programs or instructions, causing the communication device to implement the methods in any possible design or implementation of the first to fourth aspects.
  • the interface circuit is used to implement communication functions within the communication device and/or communication functions between the communication device and other devices or components.
  • the processor is used to communicate with other devices or components through the interface circuit.
  • the communication device may also include the memory.
  • the aforementioned communication device may be a terminal, or a communication/processing module in the terminal, or a chip in the terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in the terminal responsible for processing functions (such as a GPU).
  • a modem chip also known as a baseband chip
  • SoC or SIP chip containing a modem module
  • a circuit or chip in the terminal responsible for processing functions such as a GPU.
  • this application provides a communication system, including a communication device for performing the method in any possible design of the first and third aspects described above, and a communication device for performing the method in any possible design of the second and fourth aspects described above.
  • this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to fourth aspects described above.
  • this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to third aspects described above.
  • Figure 1 is a schematic diagram of a possible, non-limiting system
  • Figure 2 is a schematic diagram of a possible application framework in a communication system
  • Figure 3 is a schematic diagram of another possible application framework in a communication system
  • Figure 4 is a schematic diagram of a semantic communication method
  • Figure 5A is a schematic diagram of an application scenario provided by this application.
  • Figure 5B is a schematic diagram of an application scenario provided by this application.
  • Figure 5C is a schematic diagram of an application scenario provided by this application.
  • FIG. 6 is a flowchart illustrating a communication method provided in this application.
  • FIG. 7 is a flowchart illustrating another communication method provided in this application.
  • Figure 8 is a schematic diagram of the structure of a communication device provided in this application.
  • FIG. 9 is a schematic diagram of another communication device provided in this application.
  • Figure 10 is a schematic diagram of the structure of a terminal provided in this application.
  • Figure 1 is a possible, non-limiting system schematic diagram.
  • the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200.
  • the communication system also includes an Internet 300.
  • RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1, collectively referred to as 120).
  • RAN 100 may also include other RAN nodes, such as wireless relay equipment and/or wireless backhaul equipment (not shown in Figure 1).
  • Terminal 120 is wirelessly connected to RAN node 110.
  • RAN node 110 is wirelessly or wired connected to core network 200.
  • the core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.
  • RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems.
  • RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (Wi-Fi) system.
  • RAN 100 can also be a communication system that integrates two or more of the above systems.
  • RAN node 110 sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access.
  • Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative.
  • network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station.
  • network element 120i accessing RAN 100 through network element 120i
  • network element 120i is a base station; but for base station 110a, network element 120i is a terminal.
  • RAN node 110 and terminal 120 are sometimes both referred to as communication devices.
  • network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions
  • network elements 120a-120j can be understood as communication devices with terminal functions.
  • the RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a Wi-Fi system.
  • the RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, or a radio controller in a CRAN scenario.
  • the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment.
  • the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).
  • All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform).
  • the RAN node can also be equipped with communication modules, circuits, or chips that perform corresponding communication functions.
  • the RAN node can also be configured with program instructions for performing corresponding communication functions, as well as corresponding program instructions.
  • the RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node's functions.
  • RAN nodes collaborate to assist the terminal in achieving wireless access, with each RAN node performing a portion of the base station's functions.
  • RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs).
  • CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU).
  • RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).
  • RRUs remote radio units
  • AAUs active antenna units
  • RRHs remote radio heads
  • CU or CU-CP and CU-UP
  • DU or RU
  • RU may have different names, but those skilled in the art will understand their meaning.
  • CU can also be called O-CU (open CU)
  • DU can also be called O-DU
  • CU-CP can also be called O-CU-CP
  • CU-UP can also be called O-CU-UP
  • RU can also be called O-RU.
  • this application uses CU, CU-CP, CU-UP, DU, and RU as examples.
  • Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.
  • a terminal can be a device or module that accesses the aforementioned communication system and has corresponding communication functions.
  • a terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc.
  • Terminals can be widely used in various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc.
  • D2D device-to-device
  • V2X vehicle-to-everything
  • MTC machine-type communication
  • IoT Internet of Things
  • virtual reality augmented reality
  • industrial control autonomous driving
  • telemedicine smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc.
  • Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, transportation vehicles with wireless communication capabilities, communication modules, etc.
  • the embodiments of this application do not limit the device form of the terminal.
  • a terminal typically contains a communication module, circuit, or chip that performs the corresponding communication function.
  • the terminal can also be configured with program instructions for performing the corresponding communication function.
  • AI nodes may also be introduced into the network.
  • AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminal devices, or core network devices.
  • RAN nodes access network nodes
  • AI nodes can be deployed independently, for example, in a location other than any of the aforementioned devices, such as in the host or cloud server of an over-the-top (OTT) system.
  • AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network devices, terminal devices, or core network elements.
  • this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, these nodes can be divided based on function, such as different AI nodes being responsible for different functions.
  • AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.
  • AI nodes can be AI network elements or AI modules.
  • FIG. 2 illustrates a possible application framework in a communication system.
  • network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces.
  • These network element nodes such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the Operations Administration and Maintenance (OAM) system, are equipped with one or more AI modules (only one is shown in Figure 2 for clarity).
  • An access network node can be a single RAN node or can include multiple RAN nodes, for example, including CUs and DUs.
  • the CU and/or DU can also be equipped with one or more AI modules.
  • a CU can also be split into CU-CP and CU-UP, with one or more AI modules configured in the CU-CP and/or CU-UP.
  • AI modules are used to implement corresponding AI functions.
  • AI modules deployed in different network elements can be the same or different.
  • the models of AI modules can achieve different functions depending on the parameter configurations.
  • the models of AI modules can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and/or dimension of the input parameters), or output parameters (e.g., the type and/or dimension of the output parameters).
  • the biases in the activation function can also be referred to as the biases of the neural network.
  • the neural network mentioned above can be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).
  • DNN deep neural network
  • CNN convolutional neural network
  • RNN recurrent neural network
  • GAN generative adversarial network
  • Deep Neural Networks are artificial neural network architectures with multiple layers of nonlinear transformation units stacked in a hierarchical structure to form deep computational models. Compared to shallow neural networks, deep neural networks have more hidden layers, allowing the network model to capture more complex data structures and higher-level abstract features.
  • a CNN is a deep neural network with a convolutional structure.
  • a CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.
  • RNN is a type of recursive neural network that takes sequence data as input, recursively moves in the direction of sequence evolution, and all nodes (recurrent units) are connected in a chain-like manner.
  • GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.
  • An AI module can have one or more models.
  • a model can infer an output, which includes one or more parameters.
  • the learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.
  • Figure 3 illustrates a possible application framework in a communication system.
  • the communication system includes a RAN intelligent controller (RIC).
  • the RIC can be the AI module shown in Figure 2, used to implement AI-related functions.
  • RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs).
  • Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds.
  • Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.
  • NRT RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference.
  • NRT RICs can obtain network-side and/or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and/or RUs) and/or terminals. This information can be used as training data or inference data.
  • RAN nodes e.g., CUs, CU-CPs, CU-UPs, DUs, and/or RUs
  • This information can be used as training data or inference data.
  • NRT RICs can deliver inference results to RAN nodes and/or terminals. Inference results can be exchanged between CUs and DUs, and/or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.
  • Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference.
  • Non-real-time RICs can obtain network-side and/or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, and/or RUs) and/or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and/or terminals. Inference results can be exchanged between CUs and DUs, and/or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.
  • RAN nodes e.g., CUs, CU-CPs, CU-UPs, DUs, and/or RUs
  • This information can be used as training data or inference data, and the inference results can
  • Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.
  • RAN nodes e.g., CU, DU
  • non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.
  • raw data is typically transmitted via encoding methods, such as semantic communication.
  • Semantic communication refers to encoding raw data (including selective feature extraction and compression) and then transmitting the encoded data to achieve communication using semantically represented information.
  • data x (such as an image) is sequentially encoded by a semantic source encoder (for semantic source encoding) and a joint channel encoder (for channel encoding) to extract semantic information from data x.
  • This information can be source signal recovery or intelligent task execution.
  • a semantic source encoder can be understood as a semantic source decoding model, and a channel encoder as a channel coding model. This also includes data or models that contribute to the aforementioned encoding models.
  • the receiving end After receiving the semantic information of data x, the receiving end decodes the semantic information based on the decoder (including the semantic source decoding model and the channel decoding model), thereby recovering the semantic information as data x'.
  • the decoder including the semantic source decoding model and the channel decoding model
  • the image recovered by the receiver based on the decoder may not have perfectly accurate pixels compared to the original image, but it is semantically correct.
  • this application provides a communication method to optimize communication quality.
  • the communication method and communication device provided in this application will be further described below with reference to the accompanying drawings. It is understood that this application uses a first device and a second device as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction.
  • the method executed by the first device in this application can also be implemented by a module (e.g., a circuit, chip, or chip system) in the first device, or a logical node, logical module, or software that can implement all or part of the functions of the first device.
  • the method executed by the second device in this application can also be implemented by a module (e.g., a circuit, chip, or chip system) in the second device, or a logical node, logical module, or software that can implement all or part of the functions of the second device.
  • the first device can be an application server, terminal device, etc.; the second device can be a core network device, access network device, routing device, etc. Examples include the following application scenarios:
  • Application Scenario 1 involves an application server (such as a cloud server or application (APP) server), a network device (such as a core network device or access network device), and a terminal device (UE in the figure) that is a data receiving device.
  • the application server communicates with the User Plane Function (UPF) network elements of the core network device via a data network (DN), and the UPF network elements communicate with the terminal device via an access network (AN).
  • UPF User Plane Function
  • DN data network
  • AN access network
  • the core network device also includes various NF network elements.
  • NF network elements include some or all of the following network elements:
  • the network elements include: Network Slice Selection Function (NSSF), Authentication Server Function (AUSF), Unified Data Management (UDM), Network Exposure Function (NEF), Network Data Repository Function (NRF), Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), Application Function (AF), and Service Communication Proxy (SCP). Descriptions and functional specifications of these network elements can be found in relevant 5G protocols and will not be elaborated upon here.
  • NSF Network Slice Selection Function
  • AUSF Authentication Server Function
  • UDM Unified Data Management
  • NEF Network Exposure Function
  • NRF Network Data Repository Function
  • AMF Access and Mobility Management Function
  • SMS Session Management Function
  • PCF Policy Control Function
  • AF Application Function
  • SCP Service Communication Proxy
  • service interfaces can connect via service interfaces to invoke corresponding service operations.
  • service interfaces are typically represented by sequence numbers. For example, some or all of the following service interface sequence numbers are included: N1, N2, N3, N4, N5, N6, N7, N11, and N33. The meanings of these interface sequence numbers are as follows:
  • N1 The interface between the AMF network element and the UE, used to transmit non-access stratum (NAS) signaling (such as QoS rules from the AMF network element) to the terminal device.
  • NAS non-access stratum
  • N2 The interface between the AMF network element and the AN, used to transmit radio bearer control information from the core network side to the access network equipment.
  • N3 The interface between the AN and the UPF network element, used to transmit uplink and downlink user plane data between the access network equipment and the UPF network element.
  • N4 The interface between SMF network elements and UPF network elements, used to transmit information between the control plane and the user plane, including the distribution of forwarding rules, QoS rules, traffic statistics rules, etc. from the control plane to the user plane, as well as the reporting of information from the user plane.
  • N5 The interface between AF network elements and PCF network elements, used to transmit information between AF network elements and PCF network elements.
  • N6 The interface between the UPF network element and the DN, used to transmit uplink and downlink user data streams between the UPF network element and the DN.
  • N7 The interface between SMF network elements and PCF network elements, used to transmit information between SMF network elements and PCF network elements.
  • N11 Interface between AMF network elements and SMF network elements, used to transmit information between AMF network elements and SMF network elements.
  • N33 The interface between AF network elements and NEF network elements, used to transmit information between AF network elements and NEF network elements.
  • the aforementioned network elements or functions can be network components in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform).
  • a platform e.g., a cloud platform
  • the aforementioned network elements or functions can be implemented by a single device, by multiple devices working together, or as a functional module within a single device; this application does not specifically limit this.
  • the various NF network elements mentioned above can also be abbreviated as NF; for example, an AMF network element can be abbreviated as AMF.
  • Application Scenario 2 involves a first device (UE1 in the figure), a second device (network device), and UE2 (data receiving device).
  • UE1 is the terminal interacting with tactile users in the main domain
  • the second device is a core network device or access network device (such as AN1 or AN2 in the figure)
  • UE2 is a remotely controlled robot in another controlled domain.
  • UE1 communicates with the UPF network element of the core network device through AN1, and the UPF network element communicates with UE2 through AN2.
  • the description of the core network device is the same as in Application Scenario 1 above and will not be repeated here.
  • Application Scenario 3 involves an application server as the first device, a routing device as the second device, and the UE as the data receiving device.
  • the second device could be a Wi-Fi router, an access point (AP), or a set-top box.
  • the application server communicates with the second device via a fixed network, while the second device communicates with the UE via a Wi-Fi communication protocol.
  • the Wi-Fi communication protocol may use, but are not limited to, the following standards: 802.11, 802.11b, 802.11a/g, 802.11n, 802.11ac, and 802.11ax.
  • Figure 6 is a flowchart illustrating a communication method provided in this application. The method includes the following steps:
  • Step 601 The first device sends first information to the second device, the first information indicating the candidate model.
  • this step based on different model parameters (such as encoding rate, quantization step size, compression ratio, etc.), there are multiple candidate models (i.e., at least two).
  • model parameters such as encoding rate, quantization step size, compression ratio, etc.
  • candidate models are associated with network states. Furthermore, at least two candidate models are associated with different network states. It can be understood that the network state is determined by a device (such as a base station communicating with a data receiving device, hereinafter referred to as a third device for ease of description).
  • a device such as a base station communicating with a data receiving device, hereinafter referred to as a third device for ease of description.
  • network states can be categorized based on at least one of the following factors, including but not limited to: bandwidth, latency, and packet loss rate. For example, if the channel bandwidth corresponding to the third device at the current moment is in the first range (e.g., 5MHz-15MHz), then the current moment corresponds to one network state; if the channel bandwidth corresponding to the third device at the current moment is in the second range (e.g., 15MHz-25MHz), then the current moment corresponds to another network state. It is understood that network states can be categorized based on a single factor or a combination of factors mentioned above, and no specific limitations are imposed here.
  • network status is divided into different levels, which are related to network transmission rate, base station computing power, energy consumption, etc.
  • network status is divided into three levels: level 1 is associated with faster network transmission rates, level 2 with medium network transmission rates, and level 3 with slower network transmission rates.
  • network transmission rate is related to factors such as bandwidth, latency, and packet loss rate.
  • Network status can be divided into more levels based on the range of network transmission rates. This application does not specifically limit this, nor does it define the speed of network transmission rates.
  • these candidate models can be determined by the first device based on the attributes of the first data.
  • the first data is the data that the first device needs to send, and the attributes can also be referred to as parameters, specifications, etc.
  • the first data can be video data, image data, audio data, text data, etc.
  • the candidate model is a model for encoding the video data; that is, the candidate model is used to encode the video data.
  • the candidate model could be an AI codec model, which includes, but is not limited to, video coding models based on Convolutional Neural Networks (CNN), video coding models based on Transformers, generative video coding models, etc.
  • CNN Convolutional Neural Networks
  • the attributes of the first data include at least one of the following: data volume, frame rate, and application scenario.
  • data volume refers to the size of the first data
  • frame rate refers to the frequency of continuous image display in the first data
  • application scenario refers to the scenario in which the first data is applied (or can be understood as the display scenario).
  • application scenarios include apps, web pages, etc., meaning the application scenario can represent the required image clarity.
  • the first device can determine the compression ratio range based on the parameters of the first data, and then determine candidate models based on this compression ratio range.
  • the compression ratio range corresponding to the first data can be a large range (e.g., 40%-60%). Because different model parameters result in different compression ratios for any two candidate models, this compression ratio range generally corresponds to multiple candidate models. For example, this compression ratio range might correspond to five candidate models: h1, h2, h3, h4, and h5.
  • these candidate models can be pre-sent to the second device, or the first and second devices can pre-agree on these candidate models, and these candidate models have unique identifiers.
  • the first information can include the unique identifier of the candidate model to indicate it.
  • the first information can include model parameters to indicate the candidate model.
  • the network state can also be pre-agreed upon by the first and second devices. Therefore, the first information can indicate the network state associated with each candidate model through a mapping relationship (such as key-value pairs).
  • candidate models include h1, h2, h3, h4, and h5, and network states include two levels, level 1 and level 2; where candidate models h1, h3, and h4 are associated with the network state corresponding to level 1, and candidate models h2 and h5 are associated with the network state corresponding to level 2.
  • a candidate model can be associated with at least one network state.
  • candidate model h1 can be associated with both the network state corresponding to level 1 and the network state corresponding to level 2.
  • the first information indicates the model parameters of the candidate model, which are used by the second device to determine the target model from the candidate models, as described in step 602 below.
  • the first information also indicates the priorities of at least two candidate models, optionally associated with the same network state. It can be understood that for any given network state, the priorities of the at least two candidate models associated with that network state are different; this priority represents the priority of selecting a candidate model as the target model. For example, in descending order of priority, the candidate models associated with the network state corresponding to level 1 are h3, h1, and h4, and vice versa.
  • the priority of at least two candidate models can also be indicated by the first device by sending another message to the second device, which is not limited here.
  • the first information can be periodically sent by the first device to achieve periodic selection of the target model, ensuring the real-time compatibility of the target model with the current network status, preventing the target model from becoming inapplicable to the changed network status, and ensuring the accuracy of the target model usage.
  • Step 602 The second device selects the target model from the candidate models based on the current network status.
  • the second device can determine the current network state based on factors such as current bandwidth, latency, and packet loss rate. For a detailed description, please refer to step 601; this application will not repeat it here.
  • the second device selects a candidate model associated with the current network state, and then selects a target model from the candidate models associated with the current network state. For example, if the current network state is the network state corresponding to level 1, the candidate models associated with the current network state include h1, h3, and h4.
  • the first information also indicates the priorities of at least two candidate models associated with the current network state. Therefore, the second device can determine the target model from the at least two candidate models associated with the current network state based on their priorities.
  • the second device may select the candidate model with the highest priority among at least two candidate models associated with the current network state as the target model. For example, if the candidate models associated with the current network state are h3, h1, and h4 in descending order of priority, the second device may select candidate model h3 as the target model.
  • the second device selects the target model from at least two candidate models associated with the current network state based on the model parameters of the candidate models, the current network state, the resource scheduling status of the third device, and the priorities of at least two candidate models associated with the current network state, using a weighted summation or other calculation method.
  • the weights of the resource scheduling status of the third device, the model parameters, and the priorities can be preset values based on experience. It is understood that the weights of priorities and any model parameter differ for different network states.
  • the calculation method can also be other algorithms besides weighted summation; this application does not specifically limit its application to these methods.
  • the resource scheduling information of the third device includes, but is not limited to, the following: packet latency requirements, remaining packet latency, packet size, and the amount of resources allocated to the packet.
  • the current network status includes, but is not limited to, the following: network bandwidth, base station computing power, and energy consumption.
  • the second device can assign weights to different model parameters and priorities based on the current network status and the resource scheduling of the third device, and then perform a weighted sum based on the weights corresponding to the different model parameters and priorities to obtain the score value corresponding to each candidate model.
  • the compression rate is assigned a weight w1
  • the coding rate is assigned a weight w2
  • the priority is assigned a weight w3.
  • M is the score of the candidate model
  • q1 represents the compression ratio of the candidate model
  • q2 represents the coding rate of the candidate model
  • q3 represents the priority of the candidate model
  • w1 represents the weight of the compression ratio
  • w2 represents the weight of the coding rate
  • w3 represents the weight of the priority.
  • the second device can select a target model adapted to the current network state. For example, if the current network state is level 1 (i.e., the network transmission rate is relatively fast), then the target model selected by the second device has a lower compression ratio. It can be understood that the lower the compression ratio, the smaller the difference between the original data (i.e., the first data) and the encoded data; similarly, the closer the decoded data is to the original data, thus ensuring the clarity and accuracy of the data received by the third device while meeting the data transmission requirements. Conversely, if the current network state is level 3 (i.e., the network transmission rate is relatively slow), then the target model selected by the second device has a higher compression ratio.
  • the second device can directly select a target model from candidate models based on the model parameters of the candidate models, according to the current network state.
  • the parameters of the candidate models include, but are not limited to, encoding rate, quantization step size, etc.
  • the second device can select a target model based on multiple candidate model parameters, which is not limited in this application.
  • Step 603 The second device sends second information to the first device, the second information indicating the target model.
  • the second information also indicates the effective time of the target model, which represents the valid period for using the target model.
  • the first device encodes the first data according to the target model within the effective time.
  • the effective time includes the start time. Based on this, the first device can encode the first data according to the target model when the start time is reached.
  • the effective time includes a start time and an effective duration. Based on this, the first device can encode the first data according to the target model when the start time is reached and within the effective duration. That is, as time goes by, if the current time is no longer within the effective duration, the first device will no longer use the target model to encode the first data.
  • the effective time includes a start time and an end time. Based on this, the first device can encode the first data according to the target model within the time period from the start time to the end time.
  • the effective time may take the form of, but is not limited to, the offset of the start time from the second device's decision time, the absolute start time, a time window (the start time is within the time window), the latest start time, etc. This application does not limit the form of the effective time.
  • the second device is an access network device (such as a base station) that communicates with the third device
  • the second device can send the second information to the core network device through the N3 interface, and the core network device can then send the second information to the first device through the N6 interface.
  • Step 604 The first device encodes the first data according to the target model to obtain the second data.
  • the first device determines whether the currently used model is the target model. If so, it continues to use the target model. Otherwise, the parameters of the current model are adjusted to the parameters of the target model, i.e., the target model is used.
  • the second data is the encoded data of the first data, such as the semantic information of the first data. It can be understood that the amount of the second data is less than that of the first data.
  • the process of encoding the first data using the target model is not limited in this application.
  • Step 605 The first device sends the second data to the second device.
  • the first device sends the second data to the second device, which then forwards the second data to the third device.
  • the third device decodes it to obtain the third data.
  • the second data may contain semantic information of the first data; therefore, the third data may not be completely identical to the first data, but they are semantically identical.
  • the first device before encoding the first data, sends candidate models associated with different network states to the second device. This allows the second device, after determining the current network state, to identify the target model associated with that state from the candidate models and indicate the target model using second information. The first device can then use this target model to encode the first data, making the second data suitable for transmission under the current network state, thereby improving communication quality.
  • FIG. 7 is a flowchart illustrating a communication method provided in this application. The method includes the following steps:
  • Step 701 The second device sends third information to the first device, which indicates the current network status.
  • Step 702 The first device selects the target model from the candidate models based on the current network status.
  • the first device selects a candidate model associated with the current network status, and then selects a target model associated with the current network status from the candidate models associated with the current network status.
  • the first device can select a target model associated with the current network state based on the priority of at least two candidate models associated with the current network state.
  • the candidate model with the highest priority among the at least two candidate models associated with the current network state can be selected as the target model.
  • the third information also indicates the resource scheduling status between the second and third devices. Therefore, the first device can also select the target model associated with the current network state from at least two candidate models associated with the current network state, based on the model parameters of the candidate models, the current network state, the resource scheduling status between the second and third devices, and the priorities of at least two candidate models associated with the current network state, through a weighted summation or other calculation method. For a detailed description, refer to step 602 above; this application will not repeat it here.
  • the third information also indicates the effective time of the target model, as described in step 603 above, which will not be repeated here.
  • Step 703 The first device encodes the first data according to the target model to obtain the second data.
  • Step 704 The first device sends the second data to the second device.
  • the third information can be periodically sent by the second device. Therefore, the first device can encode the first data according to a target model associated with the current network state, making the second data suitable for transmission under the current network state, thereby improving communication quality.
  • the network device and terminal device include hardware structures and/or software modules corresponding to perform each function.
  • this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.
  • Figures 6 and 7 are schematic diagrams of the communication devices provided in the embodiments of this application. These communication devices can be used to implement the functions of the first device or the second device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.
  • the first device can be one of the terminals 120a-120j shown in Figure 1
  • the first device can be a base station 110a or 110b shown in Figure 1
  • the first device can also be a module (such as a chip) applied to the terminal or the base station.
  • the method shown in Figure 6 will be used as an example below, and the method shown in Figure 7 will not be described in detail.
  • the communication device 800 includes a processing unit 810 and a transceiver unit 820.
  • the communication device 800 is used to implement the functions of the first device or the second device in the method embodiment shown in Figure 6 above.
  • the processing unit 810 is used to send first information to the second device through the transceiver unit 820, the first information indicating a candidate model; then, it receives second information from the second device through the transceiver unit 820, the second information indicating a target model, the target model being one of the candidate models; finally, the processing unit 810 is used to encode the first data according to the target model to obtain second data, and send the second data to the third device, the third device being a data receiving device.
  • the candidate model is associated with a network state, wherein at least two candidate models are associated with different network states, and the target model is associated with the current network state.
  • the candidate models include at least two candidate models associated with the same network state, and the first information further indicates the priority of the at least two candidate models.
  • the second information further indicates the effective time of the target model; the processing unit 810 is specifically used to: encode the first data according to the target model within the effective time.
  • the effective time includes a start time
  • the processing unit 810 is specifically used to: encode the first data according to the target model when the start time is reached; or, the effective time includes a start time and an effective duration, and the processing unit 810 is specifically used to: encode the first data according to the target model when the start time is reached and within the effective duration; or, the effective time includes a start time and an end time, and the processing unit 810 is specifically used to: encode the first data according to the target model during the period from the start time to the end time.
  • the processing unit 810 is further configured to: determine the candidate model based on the attributes of the first data, wherein the attributes of the first data include at least one of the following: data volume, frame rate, and application scenario.
  • the first data is video data
  • the candidate model is a model used to encode the video data
  • the processing unit 810 is used to receive first information from the first device through the transceiver unit 820, the first information indicating a candidate model, the candidate model being used for data encoding; then, the processing unit 810 is used to send second information to the first device through the transceiver unit 820, the second information indicating the target model, the target model being one of the candidate models.
  • the candidate models are associated with network states, wherein at least two candidate models are associated with different network states; the processing unit 810 is further configured to: select the target model from the candidate models based on the current network state.
  • the processing unit 810 is specifically configured to: select at least two candidate models associated with the current network state from the candidate models; and determine the target model from the at least two candidate models according to their priorities.
  • the first information also indicates the priority of the at least two candidate models.
  • the second information also indicates the effective time of the target model.
  • the effective time includes a start time; or, the effective time includes a start time and an effective duration; or, the effective time includes a start time and an end time.
  • the processing unit 810 is further configured to receive second data from the first device through the transceiver unit 820 and send the second data to the third device, wherein the second data is obtained by the first device encoding the first data according to the target model.
  • processing unit 810 and the transceiver unit 820 can be obtained directly from the relevant description in the method embodiment shown in Figure 6, and will not be repeated here.
  • the communication device 900 includes a processor 910 and an interface circuit 920.
  • the processor 910 and the interface circuit 920 are coupled to each other.
  • the interface circuit 920 can be a transceiver or an input/output interface.
  • the communication device 900 may also include a memory 930 for storing instructions executed by the processor 910, or storing input data required by the processor 910 to execute instructions, or storing data generated after the processor 910 executes instructions.
  • the processor 910 is used to implement the function of the processing unit 810, and the interface circuit 920 is used to implement the function of the transceiver unit 820.
  • the terminal chip implements the functions of the first device in the above method embodiments.
  • the terminal chip receives information from other modules (such as radio frequency modules or antennas) in the first device, which is sent to the terminal chip by the second device; or, the terminal chip sends information to other modules (such as radio frequency modules or antennas) in the first device, which is sent to the second device by the first device.
  • the module implements the functions of the second device in the above method embodiments.
  • the module receives information from other modules (such as a radio frequency module or antenna) in the second device, information sent from the first device to the second device; or, the module sends information to other modules (such as a radio frequency module or antenna) in the second device, information sent from the second device to the first device.
  • the second device module can be the baseband chip of the second device, or a DU or other modules.
  • the DU here can be a DU under an open radio access network (O-RAN) architecture.
  • OF-RAN open radio access network
  • processors in the embodiments of this application may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.
  • CPU Central Processing Unit
  • DSP digital signal processors
  • ASIC application-specific integrated circuits
  • FPGA field-programmable gate arrays
  • a general-purpose processor may be a microprocessor or any conventional processor.
  • This application provides another example of a communication device, which includes at least one processor and at least one memory coupled together.
  • the at least one processor and the at least one memory are used to store instructions.
  • the communication device performs the method described in the above embodiments.
  • the communication device 900 includes a processor 910 and a memory 930.
  • the processor 910 and the memory 930 are coupled together.
  • the memory 930 stores some or all of the instructions.
  • the communication device 900 performs the method performed by the first device or the second device described in the above embodiments.
  • the memory may be integrated into the processor 910.
  • the method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor.
  • the software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art.
  • An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium.
  • the storage medium can also be a component of the processor.
  • the processor and storage medium can reside in an ASIC. Alternatively, the ASIC can reside in a network device or terminal.
  • the processor and storage medium can also exist as discrete components in a network device or terminal.
  • implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof.
  • software When implemented using software, it can be implemented entirely or partially in the form of a computer program product.
  • the computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of this application are performed entirely or partially.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable device.
  • the computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another.
  • the computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media.
  • the available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive.
  • the computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.
  • the terminal 1000 can correspond to the first device shown in Figure 6 and is used to implement the operation of the first device in the above embodiments.
  • the terminal includes: one or more antennas 1010, a radio frequency processing system 1020, and a processor system 1030.
  • the RF processing system 1020 receives RF signals through the antenna 1010 and sends the RF-processed signals to the processor system 1030 for further processing.
  • the processor system 1030 processes the terminal-side information and sends it to the RF processing system 1020, which then processes the signal and transmits it through the antenna 1010.
  • the radio frequency (RF) processing system 1020 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 1021 and an RF transceiver 1022.
  • the RFFE 1021 is primarily used for one or more processing operations, such as shaping, passband selection, or gain adjustment, on the RF signals received by the antenna or those to be transmitted through the antenna. It may include one or more components such as RF switches, duplexers, filters, power amplifiers, antenna tuners, and low-noise amplifiers.
  • the RFFE 1021 can be a circuit system composed of multiple discrete devices or integrated into one or more chips.
  • the RF transceiver 1022 processes the RF signals received by the RFFE into baseband/IF signals for further processing by the processor system 1030, and processes the baseband/IF signals provided by the processor system 1030 into RF signals for transmission to the RFFE 1021.
  • the baseband/IF signals transmitted between the RF transceiver 1022 and the processor system 1030 can be digital or analog signals.
  • the radio frequency transceiver 1022 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFICs).
  • processor system 1030 may include one or more processors for processing signals and executing one or more communication protocols.
  • processor system 1030 may also include memory 1036.
  • the one or more processors include at least one baseband processor 1031 (also known as a modem processor).
  • Memory 1036 is used to store data and/or computer program instructions.
  • processor system 1030 may also include one or more application processors 1032 for implementing processing of the terminal operating system and application layer.
  • Application processor 1032 may include, for example, a GPU.
  • processor system 1030 may also include one or more of a voice subsystem 1033, a multimedia subsystem 1034, or an interface circuit 1035.
  • the voice subsystem 1033 is used to process voice signals
  • the multimedia subsystem 1034 is used to handle multimedia-related operations, such as video encoding/decoding, image processing, etc.
  • the interface circuit 1035 is used to implement communication with other terminal components, such as a display 1040, an input device 1050, memory 1060, etc.
  • the aforementioned components in the processor system 1030 can communicate with each other via a bus or communication interface circuit.
  • the processor system 1030 can be packaged as a single processor chip, such as a SoC chip or a SIP chip.
  • the processor system 1030 can be a system composed of multiple chips, for example, the baseband processor 1031 can be packaged as a single chip, or packaged with part or all of the circuitry of the radio frequency processing system into a single chip.
  • memory 1036 can be on-chip memory, i.e., located on the processor system 1030 chip.
  • memory 1060 can be off-chip memory, i.e. located outside the processor system 1030 chip.
  • the baseband processor 1031 may include one or more processor cores 10311 and interface circuitry 10314.
  • the one or more processor cores 10311 are used to process signals and execute one or more communication protocols.
  • the baseband processor 1031 may also include a memory 10312 for storing at least a portion of the corresponding computer program instructions and/or data.
  • the one or more processor cores 10311 execute the computer program instructions stored in the memory 10312 to implement the relevant operations in the above method embodiments (such as determining the candidate model based on the parameters of the first data).
  • memory 10312 is used to store corresponding computer program instructions and/or data.
  • memory 10312 stores all corresponding computer program instructions and/or data for execution by processor core 10311; or it can mean that memory 10312 stores a portion of corresponding computer program instructions and/or data, including the computer program instructions and/or data currently required to be executed by processor core 10311.
  • Memory 10312 can store different portions of computer program instructions and/or data multiple times for execution by processor core 10311 to implement the relevant operations in the above method embodiments.
  • Interface circuit 10314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 1020, communicating with other subsystems and related components of processor system 1030 via bus, such as transmitting data control signals with application processor 1032, and transmitting data or computer program instructions with memory 1036 or memory 1060.
  • a baseband signal processing circuit 10313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.
  • the communication device provided in this application may be a terminal 1000, a communication module including a processor system 1030 and a radio frequency system 1020, or a baseband processor 1031.
  • the processor, processor system, application processor, baseband processor, processor circuit, or processor core mentioned above can be collectively referred to as a processor.
  • the processor may include one or more of the following: central processing unit (CPU), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), graphics processing unit (GPU), field programmable gate array (FPGA), artificial intelligence processor (AI processor), or neural processing unit (NPU).
  • CPU central processing unit
  • DSP digital signal processor
  • MPU microprocessor unit
  • MCU microcontroller unit
  • GPU graphics processing unit
  • FPGA field programmable gate array
  • AI processor artificial intelligence processor
  • NPU neural processing unit
  • the aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • PCM phase-change memory
  • ResRAM resistive random access memory
  • MRAM magnetoresistive random access memory
  • FRAM ferroelectric random access memory
  • cache register
  • ROM read-only memory
  • EPROM erasable programmable read-only memory
  • EPROM erasable programmable read-only memory
  • computer program instructions for executing the above embodiments may be stored in non-volatile memory, such as at least a portion of the aforementioned memory 1060 (e.g
  • the corresponding computer program instructions may be partially or wholly loaded onto a memory with a faster transfer speed than the processor, such as at least a portion of memory 1036 and/or memory 10312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.
  • a memory with a faster transfer speed than the processor such as at least a portion of memory 1036 and/or memory 10312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.
  • the RF transceiver 1022 and the RF front-end 1021 can also be packaged in a single chip.
  • the RF transceiver 1022, the RF front-end 1021, and the baseband processor 1031 can also be packaged in a single chip.
  • system and “network” in this application embodiment are used interchangeably.
  • “At least one” refers to one or more, and “multiple” refers to two or more.
  • “And/or” describes the relationship between related objects, indicating that three relationships can exist. For example, A and/or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural.
  • the character “/” generally indicates that the preceding and following related objects are in an “or” relationship.
  • At least one of the following” or similar expressions refer to any combination of these items, including any combination of single or plural items.
  • At least one of A, B, or C includes A, B, C, AB, AC, BC, or ABC; “at least one of A, B, and C” can also be understood as including A, B, C, AB, AC, BC, or ABC.
  • the ordinal numbers such as “first” and “second” mentioned in this application embodiment are used to distinguish multiple objects and are not used to limit the order, sequence, priority, or importance of multiple objects.
  • this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.
  • These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and/or one or more block diagrams.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and/or one or more block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种通信方法及装置，该方法应用于第一设备，第一设备为数据发送端设备。该方法中，第一设备向第二设备发送第一信息，第一信息指示候选模型；然后，第一设备接收来自第二设备的第二信息，第二信息指示目标模型，目标模型是候选模型中的一个，第二设备为网络设备；最后，第一设备根据目标模型对第一数据进行编码，得到第二数据，并发送第二数据。为此，第一设备可以使用与第二设备选择的目标模型对第一数据进行编码，使得对第一数据编码后得到的第二数据适应于第二设备传输，以此优化通信质量。

Description

一种通信方法及装置
相关申请的交叉引用
本申请要求在2024年07月04日提交中华人民共和国国家知识产权局、申请号为202410895180.8、申请名称为“一种通信方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及无线通信技术领域，尤其涉及一种通信方法及装置。
背景技术
在无线通信系统的一些应用场景中，为降低传输量、减少对传输带宽的需求，采用语义通信(Semantic Communication)。语义通信是指对原始数据进行编码(包括有选择的特征提取、压缩等)，然后传输编码后的数据，实现用语义表征信息进行通信的技术。
在面对网络波动时，语义通信的质量会下降，为此，如何优化通信质量是目前需要解决的技术问题。
发明内容
本申请实施例提供一种通信方法及装置，用于优化通信质量。
第一方面，本申请提供一种通信方法，该方法应用于第一设备，第一设备为数据发送端设备。第一设备可以是网络设备，比如第一设备为网络侧的应用服务器、应用服务器中的模块(例如电路，芯片或芯片系统等)、或者能实现全部或部分应用服务器功能的逻辑节点、逻辑模块或软件。第一设备也可以是终端设备，或者为终端设备中的芯片、单元或模块，或者为具有终端功能的通信装置，或者为具有终端功能的通信装置内部的芯片、单元或模块。在该方法中，第一设备向第二设备发送第一信息，其中，第一信息指示候选模型；然后，第一设备接收来自第二设备的第二信息，其中，第二信息指示目标模型，目标模型是候选模型中的一个，第二设备为网络设备；最后，第一设备根据目标模型对第一数据进行编码，得到第二数据，并向第三设备发送第二数据，第三设备为数据接收端设备。
采用上述方法，第一设备可以在对待传输数据(即第一数据)编码之前，向第二设备发送候选模型，以使第二设备从候选模型中选择一个适用的目标模型，并通过第二信息指示目标模型。从而第一设备可以使用该目标模型对第一数据进行编码，使得对第一数据编码后得到的第二数据适应于第二设备传输，以此优化通信质量。
一种可能的实现方式中，候选模型与网络状态关联，且至少两个候选模型关联的网络状态不同，目标模型与当前网络状态关联。
上述实现方式中，候选模型与不同的网络状态关联，以使第二设备在确定当前网络状态之后，从候选模型中确定与当前网络状态关联的目标模型，并通过第二信息指示目标模型。从而第一设备可以使用该目标模型对第一数据进行编码，使得对第一数据编码后得到的第二数据适应于在当前网络状态下进行传输，以此优化通信质量。
一种可能的实现方式中，候选模型包括与同一个网络状态关联的至少两个候选模型，第一信息还指示至少两个候选模型的优先级。
采用上述方式，针对不同的网络状态，任一网络状态可以关联至少两个候选模型，该至少两个候选模型标记有优先级，以表示至少两个候选模型对第一数据编码的优劣等级，实现从优选择，优化通信质量。
一种可能的实现方式中，所述第二信息还指示所述目标模型的生效时间；所述根据所述目标模型对第一数据进行编码，包括：在所述生效时间内根据所述目标模型对第一数据进行编码。
采用上述方式，基于网络状态的变化，通过生效时间使目标模型仅在当前时段进行使用，防止出现目标模型不适用变化后的网络状态的情况，保证目标模型使用的准确性。
一种可能的实现方式中，所述生效时间包括起始时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和生效时长，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，且在所述生效时长内，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和结束时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在所述起始时刻至所述结束时刻的时段内，根据所述目标模型对第一数据进行编码。
一种可能的实现方式中，所述向第二设备发送第一信息之前，所述方法还包括：根据所述第一数据的属性确定所述候选模型，所述第一数据的属性包括以下至少一项：数据量、帧率、应用场景。
采用上述方式，使候选模型与第一数据关联，以更好的使第二数据适应于在当前网络状态下进行传输，优化通信质量。
一种可能的实现方式中，所述第一设备为应用服务器，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为终端设备，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为应用服务器，所述第二设备为路由设备，所述第三设备为终端设备。
一种可能的实现方式中，所述第一数据为视频数据，所述候选模型为用于对所述视频数据进行编码的模型。
第二方面，本申请提供一种通信方法，该方法可以应用于第二设备，第二设备是网络设备，比如第二设备是接入网设备、接入网设备中的模块(例如电路，芯片或芯片系统等)、或者能实现全部或部分接入网设备功能的逻辑节点、逻辑模块或软件。再比如第二设备是核心网设备、核心网设备中的模块(例如电路，芯片或芯片系统等)、或者能实现全部或部分核心网设备功能的逻辑节点、逻辑模块或软件。在该方法中，第二设备接收来自第一设备的第一信息，其中，第一信息指示候选模型，候选模型用于进行数据编码；然后，向所述第一设备发送第二信息，所述其中，第二信息指示所述目标模型，目标模型是候选模型中的一个。
采用上述方法，第二设备可以从候选模型中选择目标模型，并通过第二信息指示目标模型。从而第一设备可以使用该目标模型对第一数据进行编码，使得第二数据适应于第二设备传输，以此优化通信质量。
一种可能的实现方式中，所述候选模型与网络状态关联，其中，至少两个候选模型关联的网络状态不同；基于此，第二设备根据当前网络状态从所述候选模型中选择目标模型。
一种可能的实现方式中，所述根据当前网络状态从所述候选模型中选择目标模型，包括：从候选模型中选择与当前网络状态关联的至少两个候选模型，然后根据至少两个候选模型的优先级，从至少两个候选模型中确定目标模型。
采用上述方法，第二设备可以根据当前网络状态从候选模型中选择目标模型，从而第一设备使用该目标模型对第一数据进行编码，使得第二数据适应于在当前网络状态下进行传输，以此优化通信质量。
一种可能的实现方式中，第一信息还指示至少两个候选模型的优先级。
一种可能的实现方式中，所述第二信息还指示所述目标模型的生效时间。
一种可能的实现方式中，所述生效时间包括起始时刻；或者，所述生效时间包括起始时刻和生效时长；或者，所述生效时间包括起始时刻和结束时刻。
一种可能的实现方式中，还包括：接收来自所述第一设备的第二数据，并将所述第二数据发送给第三设备，所述第二数据是所述第一设备根据所述目标模型对第一数据进行编码得到的。
一种可能的实现方式中，所述第一设备为应用服务器，所述第二设备为网络设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为终端设备，所述第二设备为网络设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为应用服务器，所述第二设备为路由设备。
第三方面，本申请提供一种通信方法，该方法应用于第一设备。在该方法中，第一设备接收来自第二设备发送的第三信息，其中，所述第三信息指示当前网络状态；然后，第一设备根据所述当前网络状态从候选模型中选择与所述当前网络状态关联的目标模型，其中，所述候选模型与网络状态关联，至少两个候选模型关联的网络状态不同；进而，第一设备根据所述目标模型对第一数据进行编码，得到第二数据，并向第三设备发送所述第二数据，所述第三设备为数据接收端设备。
一种可能的实现方式中，所述第三信息还指示所述目标模型的生效时间；所述根据所述目标模型对第一数据进行编码，包括：在所述生效时间内根据所述目标模型对第一数据进行编码。
一种可能的实现方式中，所述生效时间包括起始时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和生效时长，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，且在所述生效时长内，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和结束时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在所述起始时刻至所述结束时刻的时段内，根据所述目标模型对第一数据进行编码。
一种可能的实现方式中，所述根据所述当前网络状态候选模型中确定与所述当前网络状态关联的目标模型之前，所述方法还包括：根据所述第一数据的属性确定所述候选模型，所述第一数据的属性包括以下至少一项：数据量、帧率、应用场景。
一种可能的实现方式中，所述第一设备为应用服务器，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为终端设备，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，所述第一设备为应用服务器，所述第二设备为路由设备，所述第三设备为终端设备。
一种可能的实现方式中，所述第一数据为视频数据，所述候选模型为用于对所述视频数据进行编码的模型。
第四方面，本申请提供一种通信方法，本申请提供一种通信方法，该方法可以应用于第二设备。在该方法中，第二设备向第一设备发送第三信息，其中，所述第三信息指示当前网络状态；然后，第二设备接收来自所述第一设备的第二数据，并将所述第二数据发送给第三设备，其中，所述第二数据是所述第一设备根据所述目标模型对第一数据进行编码得到的，所述目标模型与所述当前网络状态关联。可选的，所述第二设备周期性的向第一设备发送第三信息。
第五方面，本申请提供一种通信装置，该通信装置具备实现上述第一方面、第三方面的功能，比如，该通信装置包括执行上述第一方面涉及操作所对应的模块或单元或手段(means)，该模块或单元或手段具体可以通过软件实现，或者通过硬件实现，也可以通过软件结合硬件的方式实现。
第六方面，本申请提供一种通信装置，该通信装置具备实现上述第二方面、第四方面的功能，比如，该通信装置包括执行上述第二方面涉及操作所对应的模块或单元或手段(means)，该模块或单元或手段具体可以通过软件实现，或者通过硬件实现，也可以通过软件结合硬件的方式实现。
第七方面，本申请提供一种通信装置，该通信装置包括接口电路和一个或多个处理器。该一个或多个处理器与存储器耦合。该存储器用于存储实现上述第一方面至第四方面涉及的功能的必要计算机程序或指令的部分或全部。该一个或多个处理器可执行该计算机程序或指令，当该计算机程序或指令被执行时，使得该通信装置实现上述第一方面至第四方面中任意可能的设计或实现方式中的方法。该接口电路用于实现该通信装置内的通信功能和/或该通信装置与其他装置或组件的通信功能。
在一种可能的设计中，该处理器用于通过该接口电路与其它装置或组件通信。
在一种可能的设计中，该通信装置还可以包括该存储器。
上述通信装置可以是终端，或终端中的通信/处理模组，或终端中负责通信功能的芯片如modem芯片(又称基带芯片)或包含modem模块的SoC或SIP芯片，或终端中负责处理功能的电路或芯片(如GPU)。
第八方面，本申请提供一种通信系统，包括用于执行上述第一方面、第三方面的任一种可能的设计中的方法的通信装置，和用于执行上述第二方面、第四方面的任一种可能的设计中的方法的通信装置。
第九方面，本申请提供一种计算机可读存储介质，该计算机存储介质中存储有计算机可读指令，当计算机读取并执行该计算机可读指令时，使得计算机执行上述第一方面至第四方面的任一种可能的设计中的方法。
第十方面，本申请提供一种计算机程序产品，当计算机读取并执行该计算机程序产品时，使得计算机执行上述第一方面至第三方面的任一种可能的设计中的方法。
上述第四方面至第十方面中任一方面中可以达到的技术效果，可以相应参照上述第一方面、第二方面、第三方面和/或第四方面中可以达到的技术效果描述，重复之处不予论述。
附图说明
图1为一种可能的、非限制性的系统示意图；
图2为通信系统中的一种可能的应用框架示意图；
图3为通信系统中的另一种可能的应用框架示意图；
图4为一种语义通信的示意图；
图5A为本申请提供的一种应用场景的示意图；
图5B为本申请提供的一种应用场景的示意图；
图5C为本申请提供的一种应用场景的示意图；
图6为本申请提供的一种通信方法的流程示意图；
图7为本申请提供的另一种通信方法的流程示意图；
图8为本申请提供的一种通信装置的结构示意图；
图9为本申请提供的另一种通信装置的结构示意图；
图10为本申请提供的一种终端的结构示意图。
具体实施方式
图1为一种可能的、非限制性的系统示意图。如图1所示，通信系统10包括无线接入网(radio access network，RAN)100和核心网(core network，CN)200。可选的，该通信系统还包括互联网300。RAN 100包括至少一个RAN节点(如图1中的110a和110b，统称为110)和至少一个终端(如图1中的120a-120j，统称为120)。RAN 100中还可以包括其它RAN节点，例如，无线中继设备和/或无线回传设备(图1中未示出)等。终端120通过无线的方式与RAN节点110相连。RAN节点110通过无线或有线方式与核心网200连接。核心网200中的核心网设备与RAN 100中的RAN节点110可以分别是不同的物理设备，也可以是集成了核心网逻辑功能和无线接入网逻辑功能的同一个物理设备。
RAN 100可以为第三代合作伙伴计划(3rd generation partnership project，3GPP)相关的蜂窝系统，例如，4G、5G移动通信系统、或面向未来的演进系统。RAN 100还可以是开放式接入网(open RAN，O-RAN或ORAN)、云无线接入网络(cloud radio access network，CRAN)、或者无线保真(wireless fidelity，Wi-Fi)系统。RAN 100还可以是以上两种或两种以上系统融合的通信系统。
RAN节点110，有时也可以称为接入网设备，RAN实体或接入节点等，构成通信系统的一部分，用以帮助终端实现无线接入。通信系统10中的多个RAN节点110可以为同一类型的节点，也可以为不同类型的节点。在一些场景下，RAN节点110和终端120的角色是相对的，例如，图1中网元120i可以是直升机或无人机，其可以被配置成移动基站，对于那些通过网元120i接入到RAN 100的终端120j来说，网元120i是基站；但对于基站110a来说，网元120i是终端。RAN节点110和终端120有时都称为通信装置，例如图1中网元110a和110b可以理解为具有基站功能的通信装置，网元120a-120j可以理解为具有终端功能的通信装置。
在一种可能的场景中，RAN节点可以是基站(base station)、演进型基站(evolved NodeB，eNodeB)、接入点(access point，AP)、发送接收点(transmission reception point，TRP)、下一代基站(next generation NodeB，gNB)、未来移动通信系统中的基站、或Wi-Fi系统中的接入节点等。RAN节点可以是宏基站(如图1中的110a)、微基站或室内站(如图1中的110b)、中继节点或施主节点、或者是CRAN场景下的无线控制器。可选的，RAN节点还可以是服务器，可穿戴设备，车辆或车载设备等。例如，车辆外联(vehicle to everything，V2X)技术中的接入网设备可以为路侧单元(road side unit，RSU)。本申请中的RAN节点的全部或部分功能也可以通过在硬件上运行的软件功能来实现，或者通过平台(例如云平台)上实例化的虚拟化功能来实现。RAN节点中还可以设置有执行相应通信功能的通信模组、电路或芯片。RAN节点中还可以配置有用于执行相应通信功能的程序指令以及相应的程序指令。本申请中的RAN节点还可以是能实现全部或部分RAN节点功能的逻辑节点、逻辑模块或软件。
在另一种可能的场景中，由多个RAN节点协作协助终端实现无线接入，不同RAN节点分别实现基站的部分功能。例如，RAN节点可以是集中式单元(central unit，CU)，分布式单元(distributed unit，DU)，CU-控制面(control plane，CP)，CU-用户面(user plane，UP)，或者无线单元(radio unit，RU)等。CU和DU可以是单独设置，或者也可以包括在同一个网元中，例如基带单元(baseband unit，BBU)中。RU可以包括在射频设备或者射频单元中，例如包括在射频拉远单元(remote radio unit，RRU)、有源天线处理单元(active antenna unit，AAU)或远程射频头(remote radio head，RRH)中。
在不同系统中，CU(或CU-CP和CU-UP)、DU或RU也可以有不同的名称，但是本领域的技术人员可以理解其含义。例如，在ORAN系统中，CU也可以称为O-CU(开放式CU)，DU也可以称为O-DU，CU-CP也可以称为O-CU-CP，CU-UP也可以称为O-CU-UP，RU也可以称为O-RU。为描述方便，本申请中以CU，CU-CP，CU-UP、DU和RU为例进行描述。本申请中的CU(或CU-CP、CU-UP)、DU和RU中的任一单元，可以是通过软件模块、硬件模块、或者软件模块与硬件模块结合来实现。
终端(terminal)，可以为接入上述通信系统，且具有相应通信功能的设备或模组。终端也可以称为终端设备、用户设备(user equipment，UE)、移动台、移动终端等。终端可以广泛应用于各种场景，例如，设备到设备(device-to-device，D2D)、车物(vehicle to everything，V2X)通信、机器类通信(machine-type communication，MTC)、物联网(internet of things，IOT)、虚拟现实、增强现实、工业控制、自动驾驶、远程医疗、智能电网、智能家具、智能办公、智能穿戴、智能交通、智慧城市等。终端可以是手机、平板电脑、带无线收发功能的电脑、可穿戴设备、车辆、无人机、直升机、飞机、轮船、机器人、机械臂、智能家居设备、具有无线通信功能的运输载具、通信模组等。本申请的实施例对终端的设备形态不做限定。终端内通常设置有执行相应通信功能的通信模组、电路或芯片。终端内还以配置用于执行相应通信功能的程序指令。
为了在无线网络中支持人工智能(artificial intelligence，AI)技术，网络中还可能引入AI节点。
AI节点可以部署于该通信系统中的如下位置中的一项或多项：接入网节点(RAN节点)、终端设备、或核心网设备等，或者，AI节点也可单独部署，例如，部署于上述任一项设备之外的位置，比如，过顶(over the top，OTT)系统的主机或云端服务器中。AI节点可以与通信系统中的其它设备通信，其它设备例如可以为以下中的一项或多项：网络设备，终端设备，或，核心网的网元等。
可以理解，本申请对于AI节点的数量不予限制。例如，当有多个AI节点时，多个AI节点可以基于功能进行划分，如不同的AI节点负责不同的功能。
还可以理解，AI节点可以是各自独立的设备，也可以集成于同一设备中实现不同的功能，或者可以是硬件设备中的网络元件，也可以是在专用硬件上运行的软件功能，或者是平台(例如，云平台)上实例化的虚拟化功能，本申请对于上述AI节点的具体形态不作限定。
AI节点可以为AI网元或AI模块。
图2为通信系统中的一种可能的应用框架示意图。如图2所示，通信系统中网元之间通过接口(例如NG，Xn)，或空口相连。这些网元节点，例如核心网设备、接入网节点(RAN节点)、终端或运行管理维护(operations administration and maintenance，OAM)中的一个或多个设备中设置有一个或多个AI模块(为清楚起见，图2中仅示出1个)。接入网节点可以作为单独的RAN节点，也可以包括多个RAN节点，例如，包括CU和DU。所述CU和、或DU也可以设置一个或多个AI模块。CU还可以被拆分为CU-CP和CU-UP，CU-CP和/或CU-UP中设置有一个或多个AI模块。
AI模块用以实现相应的AI功能。不同网元中部署的AI模块可以相同或不同。AI模块的模型根据不同的参数配置，可以实现不同的功能。AI模块的模型可以是基于以下一项或多项参数配置的：结构参数(例如神经网络层数、神经网络宽度、层间的连接关系、神经元的权值、神经元的激活函数、或激活函数中的偏置中的至少一项)、输入参数(例如输入参数的类型和/或输入参数的维度)、或输出参数(例如输出参数的类型和/或输出参数的维度)。其中，激活函数中的偏置还可以称为神经网络的偏置。
在一个示例中，上述神经网络可以为深度神经网络(deep neural network，DNN)、卷积神经网络(convolutional neuron network，CNN)、循环神经网络(recurrent neural networks，RNN)、生成式对抗网络(generative adversarial networks，GAN)。
DNN是一种人工神经网络架构，它具有多层非线性变换单元，这些单元以层级结构的形式堆叠在一起，从而形成了深层次的计算模型。相较于浅层神经网络，深度神经网络拥有更多的隐藏层，允许网络模型捕获更为复杂的数据内在结构和高层次的抽象特征。
CNN是一种带有卷积结构的深度神经网络。CNN包含了一个由卷积层和子采样层构成的特征抽取器。该特征抽取器可以看作是滤波器，卷积过程可以看作是使用一个可训练的滤波器与一个输入的图像或者卷积特征平面(feature map)做卷积。
RNN是一类以序列(sequence)数据为输入，在序列的演进方向进行递归且所有节点(循环单元)按链式连接的递归神经网络(recursive neural network)。
GAN是一种深度学习模型。由一个生成器和一个判别器构成，通过对抗学习的方式来训练，目的是估测数据样本的潜在分布并生成新的数据样本。
一个AI模块可以具有一个或多个模型。一个模型可以推理得到一个输出，该输出包括一个参数或者多个参数。不同模型的学习过程、训练过程、或推理过程可以部署在不同的节点或设备中，或者可以部署在相同的节点或设备中。
图3为通信系统中的一种可能的应用框架示意图。如图3所示，通信系统中包括RAN智能控制器(RAN intelligent controller，RIC)。例如，RIC可以是图2中示出的AI模块，用于实现AI相关的功能。RIC包括近实时RIC(near-real time RIC，near-RT RIC)，和非实时RIC(non-real time RIC，Non-RT RIC)。其中，非实时RIC主要处理非实时的信息，比如，对时延不敏感的数据，该数据的时延可以为秒级。实时RIC主要处理近实时的信息，比如，对时延相对敏感的数据，该数据的时延为数十毫秒级。
近实时RIC用于进行模型训练和推理。例如，用于训练AI模型，利用该AI模型进行推理。近实时RIC可以从RAN节点(例如CU、CU-CP、CU-UP、DU和/或RU)和/或终端获得网络侧和/或终端侧的信息。该信息可以作为训练数据或者推理数据。近实时RIC可以将推理结果递交给RAN节点和/或终端。CU和DU之间，和/或DU和RU之间可以交互推理结果。例如近实时RIC将推理结果递交给DU，DU将其发给RU。
非实时RIC也用于进行模型训练和推理。例如，用于训练AI模型，利用该模型进行推理。非实时RIC可以从RAN节点(例如CU、CU-CP、CU-UP、DU和/或RU)和/或终端获得网络侧和/或终端侧的信息。该信息可以作为训练数据或者推理数据，推理结果可以被递交给RAN节点和/或终端。CU和DU之间，和/或DU和RU之间可以交互推理结果，例如非实时RIC将推理结果递交给DU，由DU将其发给RU。
近实时RIC，非实时RIC也可以分别作为一个网元单独设置。近实时RIC，非实时RIC还可以作为其他设备的一部分，例如，近实时RIC设置在RAN节点中(例如，CU，DU中)，而非实时RIC设置在OAM中、云服务器中、核心网设备、或者其他网络设备中。
在一些无线通信系统的应用场景中，为降低传输量、减少对传输带宽的需求，一般会通过编码方式传输原始数据，比如采用语义通信(Semantic Communication)。语义通信是指对原始数据进行编码(包括有选择的特征提取、压缩等)，然后传输编码后的数据，实现用语义表征信息进行通信的技术。参考图4，数据x(如图片)依次通过语义信源编码器(用于进行语义信源编码)以及联合的信道编码器(用于进行信道编码)进行编码，以提取该数据x的语义信息，这些信息可以是源信号恢复或智能任务执行。一般来说，语义信源编码器可以理解为语义信源解码模型、信道编码器可以理解为信道编码模型。可以理解，还包括对上述编码模型有帮助的数据或模型。接收端在接收到数据x的语义信息之后，基于解码器(包括语义信源解码模型和信道解码模型)对语义信息解码，进而将该语义信息恢复为数据x`。以数据x为图片为例，接收端基于解码器恢复的图片与原图片相比，像素点可能不会完全正确，但语义层面正确。
然而，在面对网络波动时，不能根据实时的网络状态选择合适的编码模型，从而导致编码后的数据(即语义信息)可能出现因时延高、带宽小导致的语义信息传输时延高，使得语义通信的质量会下降，影响数据发送端和数据接收端之间的通信质量。为此，本申请提供一种通信方法，用以优化通信质量。
下面结合附图对本申请提供的通信方法及通信装置进行进一步介绍。可以理解的，本申请中是以第一设备和第二设备作为该交互示意的执行主体为例进行示意的，但本申请并不限制交互示意的执行主体，例如，本申请中由第一设备执行的方法，也可以由第一设备中的模块(例如电路，芯片或芯片系统等)、或者能实现全部或部分第一设备功能的逻辑节点、逻辑模块或软件来实现。本申请中由第二设备执行的方法，也可以由第二设备中的模块(例如电路，芯片或芯片系统等)、或者能实现全部或部分第二设备功能的逻辑节点、逻辑模块或软件来实现。其中，针对不同的应用场景，第一设备可以是应用服务器、终端设备等；第二设备可以是核心网设备、接入网设备、路由设备等。例如包括以下应用场景：
应用场景1，如图5A所示，第一设备为应用服务器(如云服务器或应用程序(Application，APP)服务器等)，第二设备为网络设备(如核心网设备或者接入网设备)，终端设备(图示中UE)为数据接收端设备。其中，应用服务器通过数据网络(data network，DN)与核心网设备的用户面功能(User Plane Function，UPF)网元进行通信，UPF网元通过接入网(Access Network，AN)与终端设备进行通信。可以理解，核心网设备还包括多种NF网元。例如，NF网元包含以下网元中的部分或者全部：
网络切片选择功能(Network Slice Selection Function，NSSF)网元、鉴权服务功能(Authentication Server Function，AUSF)网元、统一数据管理(unified data management，UDM)网元、网络开放功能(network exposure function，NEF)网元、网元数据仓库功能(NF Repository Function，NRF)网元、接入及移动性管理功能(Access and Mobility Management Function，AMF)网元、会话管理功能(session management function，SMF)网元、策略控制功能(policy control function，PCF)网元、应用层功能(Application Function，AF)、通信代理功能(The Service Communication Proxy，SCP)网元。以上各项网元的描述和功能说明可以参照5G相关协议，这里不再展开。
任意两种NF网元之间通过服务化接口连接，以调用相应的服务化操作，服务化接口一般用序列号进行表示。例如，包含以下服务化接口的序列号部分或者全部：N1、N2、N3、N4、N5、N6、N7、N11、N33，这些接口序列号的含义如下：
N1：AMF网元与UE之间的接口，用于向终端设备传递非接入层(non access stratum，NAS)信令(如包括来自AMF网元的QoS规则)等。
N2：AMF网元与AN之间的接口，用于传递核心网侧至接入网设备的无线承载控制信息等。
N3：AN与UPF网元之间的接口，用于传递接入网设备与UPF网元间的上下行用户面数据。
N4：SMF网元与UPF网元之间的接口，用于控制面与用户面之间传递信息，包括控制面向用户面的转发规则、QoS规则、流量统计规则等的下发以及用户面的信息上报。
N5：AF网元与PCF网元之间的接口，用于传递AF网元与PCF网元之间的信息。
N6：UPF网元与DN的接口，用于传递UPF网元与DN之间的上下行用户数据流。
N7：SMF网元与PCF网元之间的接口，用于传递SMF网元与PCF网元之间的信息。
N11：AMF网元与SMF网元之间的接口，用于传递AMF网元与SMF网元之间的信息。
N33：AF网元与NEF网元之间的接口，用于传递AF网元与NEF网元之间的信息。
可以理解的是，上述网元或者功能既可以是硬件设备中的网络元件，也可以是在专用硬件上运行软件功能，或者是平台(例如，云平台)上实例化的虚拟化功能。作为一种可能的实现方法，上述网元或者功能可以由一个设备实现，也可以由多个设备共同实现，还可以是一个设备内的一个功能模块，本申请实施例对此不作具体限定。另外，以上各个NF网元也可以简称为NF，比如，AMF网元可以简称为AMF。
应用场景2，如图5B所示，第一设备为终端设备(图示中UE1)，第二设备为网络设备，UE2为数据接收端设备。比如在触觉互联网中，UE1为与主域触觉用户交互的终端，第二设备为核心网设备或者接入网设备(如图示中AN1或者AN2)，UE2为另一端受控域的远程控制机器人。其中，UE1通过AN1与核心网设备的UPF网元进行通信，UPF网元通过AN2与UE2进行通信。核心网设备的描述参考上述应用场景1，在此不做赘述。
应用场景3，如图5C所示，第一设备为应用服务器，第二设备为路由设备，UE为数据接收端设备。比如第二设备为Wi-Fi路由器、接入点(Access Point，AP)、或者机顶盒等。其中，应用服务器通过固网与第二设备进行通信，第二设备通过Wi-Fi通信协议与UE进行通信。第二设备与UE基于Wi-Fi通信协议通信时，包括但是不限于采用以下标准：802.11，802.11b，802.11a/g，802.11n，802.11ac，802.11ax。
基于上述应用场景，图6为本申请提供的一种通信方法的流程示意图。该方法包括以下步骤：
步骤601：第一设备向第二设备发送第一信息，第一信息指示候选模型。
该步骤中，基于模型参数(如编码速率、量化步长、压缩率等)的不同，候选模型为多个(即至少为两个)。
一种可能的实现方式中，候选模型与网络状态关联。且这些候选模型中至少两个候选模型关联的网络状态不同。可以理解，网络状态由与数据接收端设备(为了便于描述，下面简称为第三设备)进行通信的设备(如与第三设备通信的基站)确定。
一种可能的实现方式中，网络状态可以根据以下至少一项因素进行划分，至少一项因素包括但不限于：带宽、延迟、丢包率等。比如，若当前时刻的第三设备对应的信道带宽在第一范围(如5MHz-15MHz)，那么当前时刻对应一个网络状态；若当前时刻的第三设备对应的信道带宽在第二范围(如15MHz-25MHz)，那么当前时刻对应另一个网络状态。可以理解，网络状态可以根据上述单一因素或多个因素组合进行划分，在此不做具体限定。
一种可能的实现方式中，网络状态被划分为不同的等级，其等级与网络传输速率、基站算力、能耗等关联。比如，网络状态被划分为3个等级，等级1与较快的网络传输速率关联，等级2与中等的网络传输速率关联，等级3与较慢的网络传输速率关联。可以理解，网络传输速率与带宽、延迟、丢包率等因素相关，网络状态可以根据网络传输速率的范围划分更多的等级，本申请对此不进行具体限定，且不对网络传输速率的快慢进行定义。
一种可能的实现方式中，这些候选模型可以是第一设备根据第一数据的属性确定的。其中，第一数据为第一设备需要发送的数据，属性也可以称为参数、规格等。可选的，第一数据可以是视频数据、图片数据、音频数据、文本数据等。以第一数据是视频数据为例，候选模型是对视频数据进行编码的模型，即，候选模型用于对视频数据进行编码，比如候选模型为AI Codec模型，AI Codec模型，包括但不限于基于卷积神经网络(Convolutional Neural Networks，CNN)的视频编码模型、基于Transformer的视频编码模型、基于生成式的视频编码模型等。
第一数据的属性包括以下至少一项：数据量、帧率、应用场景。其中，数据量表示第一数据的数据大小，帧率表示第一数据中图像连续显示的频率，应用场景表示第一数据所应用的场景(或者可以理解为显示的场景)。比如应用场景包括APP、网页等，即，应用场景可以表示对显示图像的清晰度要求。可选的，第一设备可以根据第一数据的参数确定压缩率范围，进而根据该压缩率范围确定候选模型。比如，第一数据的数据量较大、帧率较大、应用场景对清晰度要求较小，那么该第一数据对应的压缩率范围可以是较大的范围(如40％-60％)。因为模型参数的不同，任意两个候选模型的压缩率是不同的，所以该压缩率范围一般会对应多个候选模型。比如，该压缩率范围对应5个候选模型，分别为h1、h2、h3、h4、h5。
一种可能的实现方式中，这些候选模型可以是预先发送给第二设备的，或者说第一设备与第二设备预先约定了这些候选模型，且这些候选模型具有唯一标识。这样，第一信息可以包括候选模型的唯一标识来指示候选模型。或者，第一信息可以包括模型参数来指示候选模型。同理，网络状态也可以是第一设备与第二设备预先约定的。为此，第一信息可以通过映射关系的形式(如key-value形式)指示每个候选模型所关联的网络状态。比如，候选模型包括h1、h2、h3、h4、h5，网络状态包括2个等级，分别为等级1和等级2；其中，候选模型h1、h3、h4与等级1对应的网络状态关联，候选模型h2、h5与等级2对应的网络状态关联。可选的，一个候选模型可以关联至少一个网络状态。比如，候选模型h1分别与等级1对应的网络状态、等级2对应的网络状态关联。
一种可能的实现方式中，第一信息指示候选模型的模型参数，该模型参数被第二设备用于从候选模型中确定目标模型，具体描述参考下述步骤602。
一种可能的实现方式中，第一信息还指示至少两个候选模型的优先级，可选的，该至少两个候选模型与同一个网络状态关联。可以理解，针对任一网络状态，与该网络状态关联的至少两个候选模型的优先级是不同的，这个优先级表示将候选模型选择为目标模型的优先级。比如，按照优先级从高到底的顺序，与等级1对应的网络状态关联的候选模型分别为h3、h1、h4，反之亦然。
一种可能的实现方式中，至少两个候选模型的优先级还可以是第一设备通过向第二设备发送另一个信息指示的，本申请在此不做限定。
可选的，基于网络状态的变化，第一信息可以是第一设备周期性发送的，以此实现周期性的选择目标模型，保证目标模型与当前网络状态的实时性，防止出现目标模型不适用变化后的网络状态的情况，保证目标模型使用的准确性。
步骤602：第二设备根据当前网络状态从候选模型中选择目标模型。
一种可能的实现方式中，第二设备可以通过当前带宽、延迟、丢包率等因素确定当前网络状态，具体描述参考步骤601中的描述，本申请在此不做赘述。第二设备确定出当前网络状态之后，选择与当前网络状态关联候选模型，然后再从与当前网络状态关联候选模型中选择目标模型。比如，当前网络状态为等级1对应的网络状态，与当前网络状态关联的候选模型包括h1、h3、h4。
一种可能的实现方式中，第一信息还指示与当前网络状态关联的至少两个候选模型的优先级。因此，第二设备可以根据与当前网络状态关联的至少两个候选模型的优先级，从与当前网络状态关联的至少两个候选模型中确定目标模型。
可选的，第二设备将与当前网络状态关联的至少两个候选模型中优先级最高的候选模型作为目标模型。比如，按照优先级从高到底的顺序，与当前网络状态关联的候选模型分别为h3、h1、h4，因此，第二设备将候选模型h3选择为目标模型。
可选的，第二设备根据候选模型的模型参数、当前网络状态、第三设备的资源调度情况以及与当前网络状态关联的至少两个候选模型的优先级，通过加权求和等计算方式，从与当前网络状态关联的至少两个候选模型中选择目标模型。其中，第三设备的资源调度情况的权重、模型参数的权重、优先级的权重可以是根据经验预设的值。可以理解，不同网络状态对应的优先级的权重、任一模型参数的权重是不同的。另外，计算方式还可以为除加权求和以外的其他算法，本申请在此不做具体限定。
示例性的，第三设备的资源调度情况包括但不限于以下信息：数据包时延要求，数据包剩余时延，数据包大小，分配给数据包的资源大小等。当前网络状态包括但不限于以下信息：网络的带宽、基站算力、能耗等。
可选的，第二设备可以根据当前网络状态以及第三设备的资源调度情况为不同的模型参数以及优先级分配权重，进而根据不同的模型参数以及优先级对应的权重进行加权求和，得到每个候选模型对应的评分值。比如，压缩率分配权重w1、编码速率分配权重w2，优先级分配权重w3，候选模型对应的评分值如下述公式(1)所示：
M＝w1*q1+w2*q2+w3*q3                         公式(1)；
其中，M为候选模型的评分值，q1表示候选模型的压缩率，q2表示候选模型的编码速率，q3表示候选模型的优先级，w1表示压缩率的权重，w2表示编码速率的权重，w3表示优先级的权重。可以理解，上述公式(1)仅是示例，模型参数还可以包括其它参数，本申请在此不做限定以及赘述。
一种可能的实现方式中，第二设备可以根据当前网络状态选择适应于当前网络状态的目标模型。比如，当前网络状态为等级1(即当前网络状态的网络传输速率较快)，那么第二设备所选择的目标模型的压缩率较小。可以理解，压缩率越小，原始数据(即第一数据)与编码后的数据的差异越小，同理，解码后的数据与原始数据越接近，以此在满足数据的传输要求基础上，保证第三设备接收到的数据的清晰度和准确性。再如，当前网络状态为等级3(即当前网络状态的网络传输速率较慢)，那么第二设备所选择的目标模型的压缩率较大。可以理解，压缩率越大，编码后数据的数据量越小，以此保证数据满足传输要求。也就是说，第二设备可以基于当前网络状态，直接根据候选模型的模型参数从候选模型中选择目标模型。可以理解，候选模型的参数包括但不限于：编码速率、量化步长等，第二设备可以根据多个候选模型参数来选择目标模型，本申请在此不做限定。
步骤603：第二设备向第一设备发送第二信息，第二信息指示目标模型。
该步骤中，第二信息还指示目标模型的生效时间，该生效时间表示使用目标模型的有效时间。比如，第一设备在生效时间内根据目标模型对第一数据进行编码。
一种可能的实现方式中，生效时间包括起始时刻。基于此，第一设备可以在到达起始时刻时，根据目标模型对第一数据进行编码。
一种可能的实现方式中，生效时间包括起始时刻和生效时长。基于此，第一设备可以在到达起始时刻时，且在生效时长内，根据目标模型对第一数据进行编码。即，随着时间的推移，当前时刻不在生效时长内时，第一设备不再使用该目标模型对第一数据进行编码。
一种可能的实现方式中，生效时间包括起始时刻和结束时刻。基于此，第一设备可以在起始时刻至结束时刻的时段内，根据目标模型对第一数据进行编码。
一种可能的实现方式中，生效时间的形式包括但不限于：起始时刻距离第二设备决策时间的偏移值、绝对起始时刻、时间窗(起始时刻处于该时间窗内)，最晚起始时刻等，本申请在此不对生效时间的形式进行限定。
可选的，第二设备为与第三设备进行通信的接入网设备(如基站)，那么，第二设备可以通过N3接口将第二信息发送至核心网设备，核心网设备再通过N6接口将第二信息发送至第一设备。
步骤604：第一设备根据目标模型对第一数据进行编码，得到第二数据。
该步骤中，第一设备接收到第二信息之后，判断当前所使用的模型是否为该目标模型，若是，则继续使用该目标模型。否则，将当前模型的参数调整为该目标模型的参数，即，使用该目标模型。第二数据为对第一数据编码后的数据，比如第二数据为第一数据的语义信息。可以理解，第二数据的数据量小于第一数据。其中，使用目标模型对第一数据编码过程，本申请在此不做限定。
步骤605：第一设备向第二设备发送第二数据。
该步骤中，第一设备将第二数据发送给第二设备，以使第二设备将该第二数据发送给第三设备。第三设备接收到第二数据之后，对第二数据进行解码，进而得到第三数据。可选的，第二数据为第一数据的语义信息，那么，第三数据与第一数据可能不会完全相同，但是第三数据与第一数据在语义层面上相同。
综上，第一设备在对第一数据编码之前，向第二设备发送与不同网络状态关联的候选模型，以使第二设备在确定当前网络状态之后，从候选模型中确定与当前网络状态关联的目标模型，并通过第二信息指示目标模型。从而第一设备可以使用该目标模型对第一数据进行编码，使得第二数据适应于在当前网络状态下进行传输，以此提高通信质量。
图7为本申请提供的一种通信方法的流程示意图。该方法包括以下步骤：
步骤701：第二设备向第一设备发送第三信息，第三信息指示当前网络状态。
参考上述步骤601中对当前网络状态的描述，本申请在此不做赘述。
步骤702：第一设备根据当前网络状态从候选模型中选择目标模型。
参考上述步骤602，第一设备接收到当前网络状态之后，选择与当前网络状态关联候选模型，然后再从与当前网络状态关联候选模型中选择与当前网络状态关联的目标模型。
一种可能的实现方式中，第一设备可以根据与当前网络状态关联的至少两个候选模型的优先级选择与当前网络状态关联的目标模型。可选的，将与当前网络状态关联的至少两个候选模型中优先级最高的候选模型作为目标模型。
一种可能的实现方式中，第三信息还指示第二设备与第三设备之间的资源调度情况。因此，第一设备还可以根据候选模型的模型参数、当前网络状态、第二设备与第三设备之间的资源调度情况、以及与当前网络状态关联的至少两个候选模型的优先级，通过加权求和等计算方式，从与当前网络状态关联的至少两个候选模型中选择与当前网络状态关联的目标模型。具体描述参考上述步骤602，本申请在此不做赘述。
一种可能的实现方式中，第三信息还指示目标模型的生效时间，参考上述步骤603的描述，本申请在此不做赘述。
步骤703：第一设备根据目标模型对第一数据进行编码，得到第二数据。
参考上述步骤604，本申请在此不做赘述。
步骤704：第一设备向第二设备发送第二数据。
参考上述步骤605，本申请在此不做赘述。
综上，第三信息可以是第二设备周期性发送的。为此，第一设备可以根据与当前网络状态关联的目标模型对第一数据进行编码，使得第二数据适应于在当前网络状态下进行传输，以此提高通信质量。
可以理解的是，为了实现上述实施例中功能，网络装置和终端装置包括了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本申请中所公开的实施例描述的各示例的单元及方法步骤，本申请能够以硬件或硬件和计算机软件相结合的形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用场景和设计约束条件。
图6和图7为本申请的实施例提供的通信装置的结构示意图。这些通信装置可以用于实现上述方法实施例中第一设备或第二设备的功能，因此也能实现上述方法实施例所具备的有益效果。在本申请的实施例中，该第一设备可以是如图1所示的终端120a-120j中的一个，该第一设备可以是如图1所示的基站110a或110b，第一设备还可以是应用于终端或基站的模块(如芯片)，第一设备还可以是应用于终端或基站的模块(如芯片)。下面以图6中所示的方法进行举例，图7中所示的方法不进行赘述。
如图8所示，通信装置800包括处理单元810和收发单元820。通信装置800用于实现上述图6中所示的方法实施例中第一设备或第二设备的功能。
当通信装置600用于实现图6所示的方法实施例中第一设备的功能时：处理单元810用于通过收发单元820向第二设备发送第一信息，所述第一信息指示候选模型；然后，通过收发单元820接收来自所述第二设备的第二信息，所述第二信息指示目标模型，所述目标模型是所述候选模型中的一个；最后，处理单元810用于根据所述目标模型对第一数据进行编码，得到第二数据，并向第三设备发送所述第二数据，所述第三设备为数据接收端设备。
一种可能的实现方式中，所述候选模型与网络状态关联，其中，至少两个候选模型关联的网络状态不同，所述目标模型与当前网络状态关联。
一种可能的实现方式中，所述候选模型包括与同一个网络状态关联的至少两个候选模型，所述第一信息还指示所述至少两个候选模型的优先级。
一种可能的实现方式中，所述第二信息还指示所述目标模型的生效时间；处理单元810具体用于：在所述生效时间内根据所述目标模型对第一数据进行编码。
一种可能的实现方式中，所述生效时间包括起始时刻，处理单元810具体用于：在到达所述起始时刻时，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和生效时长，处理单元810具体用于：在到达所述起始时刻时，且在所述生效时长内，根据所述目标模型对第一数据进行编码；或者，所述生效时间包括起始时刻和结束时刻，处理单元810具体用于：在所述起始时刻至所述结束时刻的时段内，根据所述目标模型对第一数据进行编码。
一种可能的实现方式中，处理单元810还用于：根据所述第一数据的属性确定所述候选模型，所述第一数据的属性包括以下至少一项：数据量、帧率、应用场景。
一种可能的实现方式中，所述第一数据为视频数据，所述候选模型为用于对所述视频数据进行编码的模型。
当通信装置800用于实现图6所示的方法实施例中第二设备的功能时：处理单元810用于通过收发单元820接收来自第一设备的第一信息，所述第一信息指示候选模型，所述候选模型用于进行数据编码；然后，处理单元810用于通过收发单元820向所述第一设备发送第二信息，所述第二信息指示所述目标模型，所述目标模型是所述候选模型中的一个。
一种可能的实现方式中，所述候选模型与网络状态关联，其中，至少两个候选模型关联的网络状态不同；处理单元810还用于：根据当前网络状态从所述候选模型中选择所述目标模型。
一种可能的实现方式中，处理单元810具体用于：从所述候选模型中选择与当前网络状态关联的至少两个候选模型；根据所述至少两个候选模型的优先级，从所述至少两个候选模型中确定所述目标模型。
一种可能的实现方式中，所述第一信息还指示所述至少两个候选模型的优先级。
一种可能的实现方式中，所述第二信息还指示所述目标模型的生效时间。
一种可能的实现方式中，所述生效时间包括起始时刻；或者，所述生效时间包括起始时刻和生效时长；或者，所述生效时间包括起始时刻和结束时刻。
一种可能的实现方式中，处理单元810还用于通过收发单元820接收来自所述第一设备的第二数据，并将所述第二数据发送给第三设备，所述第二数据是所述第一设备根据所述目标模型对第一数据进行编码得到的。
有关上述处理单元810和收发单元820更详细的描述可以直接参考图6所示的方法实施例中相关描述直接得到，这里不加赘述。
如图9所示，通信装置900包括处理器910和接口电路920。处理器910和接口电路920之间相互耦合。可以理解的是，接口电路920可以为收发器或输入输出接口。可选的，通信装置900还可以包括存储器930，用于存储处理器910执行的指令或存储处理器910运行指令所需要的输入数据或存储处理器910运行指令后产生的数据。
当通信装置900用于实现图6所示的方法时，处理器910用于实现上述处理单元810的功能，接口电路920用于实现上述收发单元820的功能。
当上述通信装置为应用于第一设备的芯片时，该终端芯片实现上述方法实施例中第一设备的功能。该终端芯片从第一设备中的其它模块(如射频模块或天线)接收信息，该信息是第二设备发送给终端芯片的；或者，该终端芯片向第一设备中的其它模块(如射频模块或天线)发送信息，该信息是第一设备发送给第二设备的。
当上述通信装置为应用于第二设备的模块时，该模块实现上述方法实施例中第二设备的功能。该模块从第二设备中的其它模块(如射频模块或天线)接收信息，该信息是第一设备发送给第二设备的；或者，该模块向第二设备中的其它模块(如射频模块或天线)发送信息，该信息是第二设备发送给第一设备的。这里的第二设备模块可以是第二设备的基带芯片，也可以是DU或其他模块，这里的DU可以是开放式无线接入网(open radio access network，O-RAN)架构下的DU。
可以理解的是，本申请的实施例中的处理器可以是中央处理单元(Central Processing Unit，CPU)，还可以是其它通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现场可编程门阵列(Field Programmable Gate Array，FPGA)或者其它可编程逻辑器件、晶体管逻辑器件，硬件部件或者其任意组合。通用处理器可以是微处理器，也可以是任何常规的处理器。
本申请中，提供通信装置的另一种示例，该通信装置包括至少一个处理器和至少一个存储器，该至少一个处理器和该至少一个存储器耦合，该至少一个存储器用于存储指令，当该指令被该至少一个处理器执行时，使得通信装置执行上述实施例中的方法。以通信装置包括一个处理器和一个存储器为例，如图9所示，通信装置900包括一个处理器910和一个存储器930。处理器910和存储器930耦合，存储器930中存储有部分或全部指令，当存储器930中存储的指令被处理器910执行时，通信装置900执行上述实施例中第一设备或第二设备执行的方法。可选的，存储器可以集成在处理器910中。
本申请的实施例中的方法步骤可以在硬件中实现，也可以在可由处理器执行的软件指令中实现。软件指令可以由相应的软件模块组成，软件模块可以被存放于随机存取存储器、闪存、只读存储器、可编程只读存储器、可擦除可编程只读存储器、电可擦除可编程只读存储器、寄存器、硬盘、移动硬盘、CD-ROM或者本领域熟知的任何其它形式的存储介质中。一种示例性的存储介质耦合至处理器，从而使处理器能够从该存储介质读取信息，且可向该存储介质写入信息。存储介质也可以是处理器的组成部分。处理器和存储介质可以位于ASIC中。另外，该ASIC可以位于网络装置或终端中。处理器和存储介质也可以作为分立组件存在于网络装置或终端中。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机程序或指令。在计算机上加载和执行所述计算机程序或指令时，全部或部分地执行本申请实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、网络装置、用户设备或者其它可编程装置。所述计算机程序或指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机程序或指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是集成一个或多个可用介质的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，例如，软盘、硬盘、磁带；也可以是光介质，例如，数字视频光盘；还可以是半导体介质，例如，固态硬盘。该计算机可读存储介质可以是易失性或非易失性存储介质，或可包括易失性和非易失性两种类型的存储介质。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
参见图10，为本申请实施例提供的一种终端1000的结构示意图，该终端1000可对应图6中所示的第一设备，用于实现以上实施例中第一设备的操作。如图10所示，该终端包括：一个或多个天线1010、射频处理系统1020、处理器系统1030。
在下行或侧行方向上，射频处理系统1020通过天线1010接收射频信号，并将经过射频处理后的信号发送给处理器系统1030进行进一步的处理。在上行或侧行方向上，处理器系统1030将终端侧的信息进行信号处理后，发送给射频处理系统1020，射频处理系统1020对该信号进行射频处理后经过天线1010发送。
在一个例子中，射频处理系统1020作为终端对外通信的通信接口，可以包括射频前端1021(RF front end，RFFE)和射频收发机1022(RF transceiver)。RFFE 1021主要用于对天线接收到的RF信号或即将通过天线发送的RF信号进行整形、通带选择或增益等处理中的一项或多项，可以包括射频开关、双工器、滤波器、功率放大器、天线调谐和低噪声放大器等部件中的一个或多个。RFFE 1021可以是由多个分立的器件组成的电路系统，也可以被集成封装在一个或多个芯片中。射频收发机1022用于将RFFE接收的RF信号处理为基带/中频信号以供处理器系统1030进行下一步处理，以及将处理器系统1030提供的基带/中频信号处理为RF信号以发送给RFFE 1021，射频收发机1022与处理器系统1030之间传送的基带/中频信号可以是数字信号也可以是模拟信号。射频收发机1022可以由一个或多个芯片实现，该芯片通常被称为射频芯片(RFIC)。
在一个例子中，处理器系统1030可以包括一个或多个处理器用于处理信号以及执行一个或多个通信协议。可选的，处理器系统1030还可以包括存储器1036。在一个例子中，该一个或多个处理器包括至少一个基带处理器1031(又称为调制解调(modem)处理器)。存储器1036用于存储数据和/或计算机程序指令。可选的，该处理器系统1030还可以包括一个或多个应用处理器1032，用于实现对终端操作系统以及应用层的处理。应用处理器1032比如可以包括GPU。可选的，处理器系统1030还可以包括语音子系统1033，多媒体子系统1034，或接口电路1035中的一个或多个。其中，语音子系统1033用来处理语音信号，多媒体子系统1034用于处理多媒体相关的操作，如视频编解码，图像处理等，接口电路1035用于实现与其它终端部件的通信，如显示器1040，输入装置1050，存储器1060等。处理器系统1030中的上述部件可以通过总线或通信接口电路相互通信。
在一个例子中，处理器系统1030可以被封装成一个处理器芯片，如SoC芯片或SIP芯片。在一个例子中，处理器系统1030可以是多个芯片组成的系统，例如其中的基带处理器1031可以被单独封装成一个芯片，或与射频处理系统的部分或全部电路封装成一个芯片。
在一个例子中，存储器1036可以是片上存储器，即位于处理器系统1030芯片上。在一个例子中，存储器1060可以是片外存储器，即位于处理器系统1030芯片之外。
在一个例子中，基带处理器1031可以包括一个或多个处理器核10311以及接口电路10314。一个或多个处理器核10311用于处理信号以及执行一个或多个通信协议。可选的，基带处理器1031还可以包括存储器10312，存储器10312用于存储至少部分相应的计算机程序指令和/或数据。在一个例子中，一个或多个处理器核10311通过执行存储器10312中存储的计算机程序指令，来实施上述方法实施例中的相关操作(如根据所述第一数据的参数确定所述候选模型)。本公开中，存储器10312用于存储相应的计算机程序指令和/或数据，可以是指存储器10312用于存储全部相应的计算机程序指令和/或数据供处理器核10311执行；也可以是指存储器10312用于存储部分相应的计算机程序指令和/或数据，该部分相应的计算机程序指令和/或数据包括当前需要处理器核10311执行的计算机程序指令和/或数据，存储器10312可以通过多次存入不同部分计算机程序指令和/或数据供处理器核10311执行以实施上述方法实施例中的相关操作。接口电路10314作为通信接口用于实现和其它部件的通信，如与射频处理系统1020传输信号，通过总线与处理器系统1030的其它子系统和相关部件通信，如与应用处理器1032之间传输数据控制信号，与存储器1036或存储器1060之间传输数据或计算机程序指令。可选的，为了降低处理器核的负载，还可以设置基带信号处理电路10313来实现至少部分基带信号的处理工作，包括信号的解调，调制，编码或解码等中的一种或多种。
在一个例子中，本申请提供的通信装置可以是终端1000，包含处理器系统1030及射频系统1020的通信模组，处理器系统1030，或基带处理器1031。
上述处理器，处理器系统，应用处理器，基带处理器，处理器电路或处理器核可以统称为处理器，该处理器可以包括中央处理单元(central processing unit，CPU)、数字信号处理器(digital signal processor，DSP)、微处理器(microprocessor unit，MPU)、微控制器(microcontroller unit，MCU)、图形处理器(graphics processing unit，GPU)、现场可编程门阵列(field programmable gate array，FPGA)、人工智能处理器(artificial intelligence processor，AI processor)或神经网络处理器(neural processing unit，NPU)中的一个或者多个组合。
上述存储器可以包括如下存储介质中的一个或多个：如随机存取存储器(random access memory，RAM)，静态随机存取存储器(static RAM，SRAM)，动态随机存取存储器(dynamic RAM，DRAM)，相变存储器(phase-change memory，PCM)，电阻式随机存取存储器(resistive RAM，ReRAM)，磁阻式随机存取存储器(magnetoresistive RAM，MRAM)，铁电随机存取存储器(ferroelectric RAM，FRAM)，缓存cache，寄存器register，只读存储器(read-only memory，ROM)，快闪存储器(flash memory)，可擦除可编程式只读存储器(erasable programmable ROM，EPROM)，硬盘(hard disk)等。在一个例子中，用于执行上述实施例的计算机程序指令，可以存储在非易失性存储器上，如上述存储器1060的至少一部分(如可以是ROM，flash memory，EPROM，或hard disk中的一个或多个)。在终端运行时，相应的计算机程序指令可以部分或全部被加载到和处理器传输速度更快的存储器上，如上述存储器1036和/或存储器10312的至少一部分(如可以是RAM，SRAM，DRAM，PCM，RERAM，MRAM，FRAM，缓存cache，或register中的一个或多个)，供处理器执行以实现上述方法实施例中的步骤。
在一个例子中，射频收发机1022与射频前端1021也可以封装在一个芯片中。在一个例子中，射频收发机1022，射频前端1021及基带处理器1031也可以封装在一个芯片中。
本申请实施例中的术语“系统”和“网络”可被互换使用。“至少一种”是指一种或者多种，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A、同时存在A和B、单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如“A，B或C中的至少一个”包括A，B，C，AB，AC，BC或ABC，“A，B和C中的至少一个”也可以理解为包括A，B，C，AB，AC，BC或ABC。以及，除非有特别说明，本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (19)

  1. 一种通信方法，其特征在于，应用于第一设备，所述第一设备为数据发送端设备，包括：
    向第二设备发送第一信息，所述第一信息指示候选模型；
    接收来自所述第二设备的第二信息，所述第二信息指示目标模型，所述目标模型是所述候选模型中的一个；
    根据所述目标模型对第一数据进行编码，得到第二数据，并向第三设备发送所述第二数据，所述第三设备为数据接收端设备。
  2. 如权利要求1所述的方法，其特征在于，所述候选模型与网络状态关联，其中，至少两个候选模型关联的网络状态不同，所述目标模型与当前网络状态关联。
  3. 如权利要求2所述的方法，其特征在于，所述候选模型包括与同一个网络状态关联的至少两个候选模型，所述第一信息还指示所述至少两个候选模型的优先级。
  4. 如权利要求1-3任一项所述的方法，其特征在于，所述第二信息还指示所述目标模型的生效时间；
    所述根据所述目标模型对第一数据进行编码，包括：
    在所述生效时间内根据所述目标模型对第一数据进行编码。
  5. 如权利要求4所述的方法，其特征在于，所述生效时间包括起始时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，根据所述目标模型对第一数据进行编码；或者，
    所述生效时间包括起始时刻和生效时长，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在到达所述起始时刻时，且在所述生效时长内，根据所述目标模型对第一数据进行编码；或者，
    所述生效时间包括起始时刻和结束时刻，所述在所述生效时间内根据所述目标模型对第一数据进行编码，包括：在所述起始时刻至所述结束时刻的时段内，根据所述目标模型对第一数据进行编码。
  6. 如权利要求1-5任一项所述的方法，其特征在于，所述向第二设备发送第一信息之前，所述方法还包括：
    根据所述第一数据的属性确定所述候选模型，所述第一数据的属性包括以下至少一项：数据量、帧率、应用场景。
  7. 如权利要求1-6任一项所述的方法，其特征在于，所述第一设备为应用服务器，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，
    所述第一设备为终端设备，所述第二设备为网络设备，所述第三设备为终端设备，其中，所述网络设备为核心网设备或接入网设备；或者，
    所述第一设备为应用服务器，所述第二设备为路由设备，所述第三设备为终端设备。
  8. 如权利要求1-7任一项所述的方法，其特征在于，所述第一数据为视频数据，所述候选模型为用于对所述视频数据进行编码的模型。
  9. 一种通信方法，其特征在于，应用于第二设备，所述第二设备为网络设备，包括：
    接收来自第一设备的第一信息，所述第一信息指示候选模型，所述候选模型用于进行数据编码；
    向所述第一设备发送第二信息，所述第二信息指示目标模型，所述目标模型是所述候选模型中的一个。
  10. 如权利要求9所述的方法，其特征在于，所述候选模型与网络状态关联，其中，至少两个候选模型关联的网络状态不同；还包括：
    根据当前网络状态从所述候选模型中选择所述目标模型。
  11. 如权利要求10所述的方法，其特征在于，所述根据当前网络状态从所述候选模型中选择目标模型，包括：
    从所述候选模型中选择与当前网络状态关联的至少两个候选模型；
    根据所述至少两个候选模型的优先级，从所述至少两个候选模型中确定所述目标模型。
  12. 如权利要求11所述的方法，其特征在于，所述第一信息还指示所述至少两个候选模型的优先级。
  13. 如权利要求9-12任一项所述的方法，其特征在于，所述第二信息还指示所述目标模型的生效时间。
  14. 如权利要求13所述的方法，其特征在于，所述生效时间包括起始时刻；或者，所述生效时间包括起始时刻和生效时长；或者，所述生效时间包括起始时刻和结束时刻。
  15. 如权利要求9-14任一项所述的方法，其特征在于，所述第一设备为应用服务器，所述第二设备为网络设备，其中，所述网络设备为核心网设备或接入网设备；或者，
    所述第一设备为终端设备，所述第二设备为网络设备，其中，所述网络设备为核心网设备或接入网设备；或者，
    所述第一设备为应用服务器，所述第二设备为路由设备。
  16. 一种通信装置，其特征在于，包括用于执行权利要求1至8中任一项所述方法的模块。
  17. 一种通信装置，其特征在于，包括用于执行权利要求9至15中任一项所述方法的模块。
  18. 一种计算机程序产品，其特征在于，所述计算机程序产品包括指令，当所述指令被运行时，使得如权利要求1至8、或权利要求9至15中任一项所述的方法被执行。
  19. 一种计算机可读存储介质，其特征在于，所述存储介质中存储有计算机程序或指令，当所述计算机程序或指令被执行时，实现权利要求1至8、或权利要求9至15中任一项所述方法。
PCT/CN2025/100961 2024-07-04 2025-06-13 一种通信方法及装置 Pending WO2026007673A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410895180.8 2024-07-04
CN202410895180.8A CN121283562A (zh) 2024-07-04 2024-07-04 一种通信方法及装置

Publications (1)

Publication Number Publication Date
WO2026007673A1 true WO2026007673A1 (zh) 2026-01-08

Family

ID=98236048

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/100961 Pending WO2026007673A1 (zh) 2024-07-04 2025-06-13 一种通信方法及装置

Country Status (2)

Country Link
CN (1) CN121283562A (zh)
WO (1) WO2026007673A1 (zh)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114153593A (zh) * 2021-10-29 2022-03-08 北京邮电大学 业务处理的方法、装置、电子设备及介质
CN116346279A (zh) * 2021-12-25 2023-06-27 大唐移动通信设备有限公司 信息处理方法、装置、终端及网络设备
US20240107073A1 (en) * 2021-06-11 2024-03-28 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Encoding method, decoding method, bitstream, encoder, decoder, system and storage medium

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20240107073A1 (en) * 2021-06-11 2024-03-28 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Encoding method, decoding method, bitstream, encoder, decoder, system and storage medium
CN114153593A (zh) * 2021-10-29 2022-03-08 北京邮电大学 业务处理的方法、装置、电子设备及介质
CN116346279A (zh) * 2021-12-25 2023-06-27 大唐移动通信设备有限公司 信息处理方法、装置、终端及网络设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
JINQIANG XING, OPPO: "On testability issues for two-sided AI/ML model", 3GPP DRAFT; R4-2305433; TYPE OTHER; FS_NR_AIML_AIR, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG4, no. Online; 20230417 - 20230426, 10 April 2023 (2023-04-10), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052286599 *

Also Published As

Publication number Publication date
CN121283562A (zh) 2026-01-06

Similar Documents

Publication Publication Date Title
JP7513837B2 (ja) 通信方法および装置
WO2024198976A1 (zh) 一种切分点确定方法及装置
WO2025236971A1 (zh) 人工智能优先级通知方法及相关装置
WO2025152615A1 (zh) 一种通信的方法和通信装置
WO2026007673A1 (zh) 一种通信方法及装置
WO2026056733A1 (zh) 一种通信方法及通信装置
WO2026067052A1 (zh) 通信方法、装置及存储介质
WO2026001748A1 (zh) 传输控制方法及通信装置
WO2026016729A1 (zh) 通信系统中基于ai模型的任务分配方法及相关产品
WO2025228043A1 (zh) 一种视频数据的上行传输方法及通信装置
WO2026040740A1 (zh) 通信方法和通信装置
US20260025320A1 (en) Communication method and apparatus, and computer-readable storage medium
WO2026020914A1 (zh) 一种通信方法、通信装置及通信系统
WO2026037075A1 (zh) 一种资源占用的方法和通信装置
WO2026067006A1 (zh) 一种通信方法及装置
WO2025228045A1 (zh) 信道质量指示cqi上报方法、通信装置、芯片、计算机可读存储介质及计算机程序产品
WO2026016914A1 (zh) 通信系统中模型功能对齐的方法和通信装置
WO2026091949A1 (zh) 通信方法及装置
WO2025246380A1 (zh) 一种任务处理方法及通信装置
WO2025156768A1 (zh) 一种用于测量的方法和通信装置
WO2025241605A1 (zh) 通信方法和通信装置
WO2025218414A1 (zh) 通信系统中任务执行的方法及相关装置
WO2025107925A1 (zh) 一种通信方法及装置
WO2026066972A1 (zh) 通信方法及装置、系统
WO2026031851A1 (zh) 一种通信方法及相关装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25832027

Country of ref document: EP

Kind code of ref document: A1