WO2023221059A1 - 无线通信方法、装置、设备、存储介质及程序产品 - Google Patents

无线通信方法、装置、设备、存储介质及程序产品 Download PDF

Info

Publication number
WO2023221059A1
WO2023221059A1 PCT/CN2022/093968 CN2022093968W WO2023221059A1 WO 2023221059 A1 WO2023221059 A1 WO 2023221059A1 CN 2022093968 W CN2022093968 W CN 2022093968W WO 2023221059 A1 WO2023221059 A1 WO 2023221059A1
Authority
WO
WIPO (PCT)
Prior art keywords
terminal device
delay
information
target
relay terminal
Prior art date
Application number
PCT/CN2022/093968
Other languages
English (en)
French (fr)
Inventor
陈景然
Original Assignee
Oppo广东移动通信有限公司
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 Oppo广东移动通信有限公司 filed Critical Oppo广东移动通信有限公司
Priority to PCT/CN2022/093968 priority Critical patent/WO2023221059A1/zh
Publication of WO2023221059A1 publication Critical patent/WO2023221059A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W40/00—Communication routing or communication path finding
    • H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
    • H04W40/22—Communication route or path selection, e.g. power-based or shortest path routing using selective relaying for reaching a BTS [Base Transceiver Station] or an access point

Definitions

  • the embodiments of the present application relate to the field of communication technology, and in particular, to a wireless communication method, device, equipment, storage medium and program product.
  • terminal devices such as mobile terminals
  • AI Artificial Intelligence, artificial intelligence
  • ML Machine Learning, machine learning
  • the FL (Federated Learning) server completes the training of the global model by aggregating the local training results reported by each terminal device.
  • a machine learning architecture based on Prose Proximity-based Services, short-range communication services/proximity services
  • Prose can be used to send the intermediate results of model training to other terminal devices, and the other terminal devices Complete subsequent calculations.
  • Embodiments of the present application provide a wireless communication method, device, equipment, storage medium and program product.
  • the technical solutions are as follows:
  • a wireless communication method is provided.
  • the method is executed by a relay terminal device.
  • the method includes:
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device to the server
  • QoS Quality of Service
  • Quality of Service control is performed based on the end-to-end transmission delay.
  • a wireless communication method is provided.
  • the method is executed by a remote terminal device.
  • the method includes:
  • the first information is used to determine the end-to-end transmission delay corresponding to the execution result of the target AI operation for QoS control.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device. Transmission delay to the server.
  • a wireless communication device includes:
  • a receiving module configured to receive the first information from a remote terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation;
  • Determining module configured to determine, based on the first information, the end-to-end transmission delay corresponding to the execution result of the target AI operation.
  • the end-to-end transmission delay refers to the time from the remote terminal device to the server. transmission delay;
  • a control module configured to perform QoS control based on the end-to-end transmission delay.
  • a wireless communication device includes:
  • a sending module configured to send the first information to the relay terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation;
  • the first information is used to determine the end-to-end transmission delay corresponding to the execution result of the target AI operation for QoS control.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device. Transmission delay to the server.
  • a terminal device includes a processor and a memory.
  • a computer program is stored in the memory.
  • the processor executes the computer program to implement the above relay terminal.
  • the wireless communication method performed by the device or remote terminal device.
  • a computer-readable storage medium is provided.
  • a computer program is stored in the storage medium, and the computer program is used to be executed by a processor to implement the above-mentioned relay terminal device or remote terminal. Wireless communication method performed by terminal equipment.
  • a chip is provided.
  • the chip includes programmable logic circuits and/or program instructions. When the chip is running, it is used to implement the above-mentioned relay terminal equipment or remote terminal equipment. The wireless communication method implemented.
  • a computer program product includes computer instructions.
  • the computer instructions are stored in a computer-readable storage medium.
  • a processor reads the instructions from the computer-readable storage medium.
  • the remote terminal device sends the first information to the relay terminal device, and the relay terminal device determines the end-to-end transmission delay of the execution result of the target AI operation from the remote terminal device to the server based on the first information.
  • the target AI operation It is the AI operation completed by the cooperation of these two terminal devices, which enables the relay terminal device to perform accurate QoS control based on the end-to-end transmission delay. In the scenario where the AI operation is completed through cooperation based on the relay method, the AI operation can still be guaranteed. Operation results are sent to the server on time, improving reliability.
  • Figure 1 is a schematic diagram of a network architecture provided by an embodiment of the present application.
  • Figure 2 is a schematic diagram of a network architecture provided by another embodiment of the present application.
  • Figure 3 is a schematic diagram of a network architecture provided by another embodiment of the present application.
  • Figure 4 is a schematic diagram of a federated learning architecture provided by an embodiment of the present application.
  • Figure 5 is a schematic diagram of the federated learning architecture using the Prose method provided by an embodiment of the present application.
  • Figure 6 is a schematic diagram of the Prose architecture provided by an embodiment of the present application.
  • Figure 7 is a schematic diagram of QoS processing under the Prose architecture provided by an embodiment of the present application.
  • Figure 8 is a schematic diagram of a relay-based communication connection establishment process provided by an embodiment of the present application.
  • Figure 9 is a flow chart of a wireless communication method provided by an embodiment of the present application.
  • Figure 10 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 11 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 12 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 13 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 14 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 15 is a flow chart of a wireless communication method provided by another embodiment of the present application.
  • Figure 16 is a block diagram of a wireless communication device provided by an embodiment of the present application.
  • Figure 17 is a block diagram of a wireless communication device provided by another embodiment of the present application.
  • Figure 18 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.
  • GSM Global System of Mobile communication
  • CDMA Code Division Multiple Access
  • WCDMA broadband code division multiple access
  • GPRS General Packet Radio Service
  • LTE Long Term Evolution
  • LTE-A Advanced long term evolution
  • NR New Radio
  • NTN Non-Terrestrial Networks
  • UMTS Universal Mobile Telecommunication System
  • WLAN Wireless Local Area Networks
  • WiFi wireless fidelity
  • the communication system in the embodiment of this application can be applied to a carrier aggregation (Carrier Aggregation, CA) scenario, a dual connectivity (Dual Connectivity, DC) scenario, or a standalone (Standalone, SA) network deployment scenario.
  • Carrier Aggregation, CA Carrier Aggregation, CA
  • DC Dual Connectivity
  • SA standalone
  • the communication system in the embodiment of the present application can be applied to the unlicensed spectrum, where the unlicensed spectrum can also be considered as a shared spectrum; or the communication system in the embodiment of the present application can also be applied to the licensed spectrum, where the licensed spectrum can also be Considered a non-shared spectrum.
  • Non-Terrestrial Networks NTN
  • Terrestrial Networks TN
  • the network architecture may include: terminal equipment 10, access network equipment 20 and core network elements 30.
  • the terminal equipment 10 may refer to a UE (User Equipment), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a wireless communication device, a user agent or a user device.
  • the terminal device 10 may also be a cellular phone, a cordless phone, a SIP phone, a WLL (Wireless Local Loop, wireless local loop) station, a PDA (Personal Digital Assistant, personal digital assistant), a handheld mobile phone with a wireless communication function.
  • terminal devices Equipment, computing equipment or other processing equipment connected to wireless modems, vehicle-mounted equipment, wearable devices, terminal equipment in 5GS or terminal equipment in the future evolution of PLMN (Public Land Mobi1e Network, public land mobile communication network), etc.
  • PLMN Public Land Mobi1e Network, public land mobile communication network
  • terminal devices 10 The number of terminal devices 10 is usually multiple, and one or more terminal devices 10 may be distributed in the cell managed by each access network device 20 .
  • the access network device 20 is a device deployed in the access network to provide wireless communication functions for the terminal device 10 .
  • the access network device 20 may include various forms of macro base stations, micro base stations, relay stations, access points, etc.
  • the names of devices with access network device functions may be different. For example, in 5G NR systems, they are called gNodeB or gNB. As communication technology evolves, the name "access network equipment" may change.
  • access network devices For convenience of description, in the embodiment of the present application, the above-mentioned devices that provide wireless communication functions for the terminal device 10 are collectively referred to as access network devices.
  • a communication relationship can be established between the terminal device 10 and the core network element 30.
  • the access network device 20 may be EUTRAN (Evolved Universal Terrestrial Radio Access Network, Evolved Universal Terrestrial Wireless Network) or one or more eNodeBs in EUTRAN;
  • EUTRAN Evolved Universal Terrestrial Radio Access Network
  • the access network device 20 may be a RAN (Radio Access Network) or one or more gNBs in the RAN.
  • the core network element 30 is a network element deployed in the core network.
  • the functions of the core network element 30 are mainly to provide user connections, manage users and carry services, and serve as an interface to the external network for the bearer network.
  • the core network elements in the 5G NR system can include AMF (Access and Mobility Management Function, access and mobility management function), UPF (User Plane Function, user plane function) and SMF (Session Management Function, session management function) ) and other network elements.
  • core network elements can be regarded as functional entities, and one or more core network elements can be deployed on a physical device.
  • the access network device 20 and the core network element 30 communicate with each other through some air interface technology, such as the NG interface in the 5G NR system.
  • the access network device 20 and the terminal device 10 communicate with each other through some air interface technology, such as the Uu interface.
  • the "5G NR system" in the embodiments of this application may also be called a 5G system or an NR system, but those skilled in the art can understand its meaning.
  • the technical solution described in the embodiment of this application can be applied to the LTE system, the 5G NR system, the subsequent evolution system of the 5G NR system, and can also be applied to applications such as NB-IoT (Narrow Band Internet of Things, narrowband Internet of Things) systems and other communication systems, this application does not limit this.
  • NB-IoT Near Band Internet of Things, narrowband Internet of Things
  • the access network equipment can provide services for the cell, and the terminal equipment communicates with the access network equipment through the transmission resources (for example, frequency domain resources, or spectrum resources) on the carrier used by the cell.
  • the cell can be a cell corresponding to the access network equipment (such as a base station).
  • the cell can belong to a macro base station or a base station corresponding to a small cell (Small cell).
  • the small cell here can include: urban cell (Metro cell), micro cell Micro cell, Pico cell, Femto cell, etc. These small cells have the characteristics of small coverage and low transmit power, and are suitable for providing high-rate data transmission services.
  • the system architecture 200 may include: UE (that is, the "terminal equipment” introduced above), (R)AN ((Radio) Access Network, (wireless) access network), Core (core network) ) and DN (Data Network, data network).
  • UE, (R)AN, and Core are the main components of the architecture. Logically, they can be divided into two parts: the user plane and the control plane. The control plane is responsible for the management of the mobile network, and the user plane is responsible for the transmission of business data.
  • the NG2 reference point is located between the (R)AN control plane and the Core control plane
  • the NG3 reference point is located between the (R)AN user plane and the Core user plane
  • the NG6 reference point is located between the Core user plane and the data network.
  • the UE It is the entrance for mobile users to interact with the network. It can provide basic computing capabilities and storage capabilities, display business windows to users, and receive user operation inputs. The UE will use next-generation air interface technology to establish signal connections and data connections with (R)AN to transmit control signals and business data to the mobile network.
  • R next-generation air interface technology
  • (R)AN Similar to base stations in traditional networks, it is deployed close to the UE to provide network access functions for authorized users in specific areas, and can use transmission tunnels of different qualities to transmit user data according to user levels, business needs, etc. .
  • (R)AN can manage its own resources, utilize them rationally, provide access services to UEs on demand, and forward control signals and user data between UEs and the core network.
  • Core responsible for maintaining the subscription data of the mobile network, managing the network elements of the mobile network, and providing functions such as session management, mobility management, policy management, and security authentication for the UE.
  • the UE When the UE registers, it provides network access authentication for the UE; when the UE has a service request, it allocates network resources to the UE; when the UE moves, it updates network resources for the UE; when the UE is idle, it provides a fast recovery mechanism for the UE:
  • network resources are released for the UE; when the UE has service data, it provides data routing functions for the UE, such as forwarding the uplink data to the DN: or receiving the UE downlink data from the DN and forwarding it to the (R)AN, thus Sent to UE.
  • the DN It is a data network that provides business services to users.
  • the client is located in the UE and the server is located in the data network.
  • the data network can be a private network, such as a local area network, or an external network that is not controlled by the operator, such as the Internet, or a proprietary network jointly deployed by the operator, such as configuring IMS (IP Multimedia Subsystem, IP Multimedia Subsystem) )Serve.
  • IMS IP Multimedia Subsystem, IP Multimedia Subsystem
  • IP Multimedia Subsystem IP Multimedia Subsystem
  • the core network user plane includes UPF; the core network control plane includes AUSF (Authentication Server Function, authentication server function network element), AMF, SMF, NSSF (Network Slice Selection Function) , network slicing selection function network element), NEF (Network Exposure Function, network open function network element), NRF (Network Repository Function, network storage function network element), UDM (Unified Data Management, unified data management network element), PCF ( Policy Control Function, policy control function network element), AF (Application Function, application function network element).
  • UPF User Planet Configuration Server Function, authentication server function network element
  • AMF Access Management Function
  • SMF Session Selection Function
  • NSSF Network Slice Selection Function
  • NEF Network Exposure Function, network open function network element
  • NRF Network Repository Function, network storage function network element
  • UDM Unified Data Management, unified data management network element
  • PCF Policy Control Function, policy control function network element
  • AF Application Function, application function network element
  • the UE performs AS (Access Stratum, access layer) connection with (R)AN through the Uu port, exchanges AS messages and wireless data transmission, and the UE performs NAS (Non Access Stratum, Non Access Stratum, Access Layer) with the AMF through the N1 port. non-access layer) connection and exchange NAS messages.
  • AMF is the mobility management function in the core network
  • SMF is the session management function in the core network.
  • PCF is the policy management function in the core network and is responsible for formulating policies related to UE mobility management, session management, and charging.
  • UPF is the user plane function in the core network. It transmits data with the external data network through the N6 interface and with (R)AN through the N3 interface.
  • the interface names between the various network elements in Figures 2 and 3 are just examples. In specific implementations, the names of the interfaces may be other names, which are not specifically limited in the embodiments of this application.
  • the names of various network elements (such as SMF, AF, UPF, etc.) included in Figures 2 and 3 are only examples and do not limit the functions of the network elements themselves.
  • each of the above network elements may also have other names, which are not specifically limited in the embodiments of this application.
  • some or all of the above-mentioned network elements may use the terminology used in 5G, or may adopt other names, etc., which will be described uniformly here and will not be described in detail below.
  • the names of the above-mentioned messages (or signaling) transmitted between various network elements are only examples and do not constitute any limitation on the function of the messages themselves.
  • terminal devices such as mobile terminals
  • more and more terminal devices can collect valuable training data that is essential for AI or ML model training.
  • small sample data collected by terminal devices is of great significance for training global models.
  • the FL server completes the training of the global model by aggregating the local training results reported by each terminal device.
  • the terminal device can use local training data to perform training on the global model downloaded from the FL server, and then report the intermediate training results (such as DNN (Deep Neural Network) to the FL server through the uplink channel) gradient).
  • the FL server then aggregates the collected gradients and updates the global model.
  • the FL server distributes the updated global model to the terminal devices participating in federated learning through the downlink channel, and the terminal devices perform the next iterative training on this updated model.
  • the terminal equipment outside the coverage is the remote terminal equipment (can be called Remote UE)
  • the terminal equipment within the coverage is the relay terminal equipment (can be called Relay UE)
  • the Remote UE uses Relay UE to send the result to FL server to ensure the smooth progress of federated learning.
  • Its architecture diagram is shown in Figure 5.
  • a UE with Prose capability can communicate directly with another UE with Prose capability through the PC5 interface.
  • a UE When a UE can connect to the external data network through the 5G network and also has Prose capability, this UE can act as a RelayUE.
  • Another Remote UE with Prose capability can establish a direct connection with the RelayUE through the PC5 interface, and then the RelayUE establishes a PDU with the 5G network. The session interacts with the external network, as shown in Figure 6.
  • Relay UE has a mapping mechanism between 5QI (5G QoS Identifier, 5G Service Quality Identifier) and PQI (PC5 5G QoS Identifier, 5G Service Quality Identifier on the PC5 interface).
  • SMF When a QoS flow is initiated through the network, SMF generates QoS Flow level QoS parameters based on PCC rules and local configuration (for example, 5QI, GFBR (Guaranteed Flow Bit Rate, guaranteed flow bit rate), MFBR (Maximum Flow Bit Rate, Maximum stream bit rate)), and informed to the Relay UE during the PDU session establishment or modification process.
  • Relay UE determines the QoS parameters of PC5QoS flow based on the QoS mapping mechanism. For example, PQI, GFBR and MFBR of PC5QoS flow are set to be equal to the value of QoS flow.
  • Remote UE When a PC5 QoS flow is initiated or modified by Remote UE, Remote UE provides QoS info (such as PQI, GFBR, MFBR) to Relay UE.
  • QoS info such as PQI, GFBR, MFBR
  • Relay UE translates QoS info into end-to-end QoS requirements. If the QoS mapping mechanism can support end-to-end QoS requirements, Relay UE determines 5QI for QoS control of Uu and PQI for QoS control of PC5. For example, for PDB (Packet Delay Budget) requirements, the end-to-end delay requirement is 100ms, then the PQI can be 20ms, and the 5QI can be 80ms.
  • PDB Packet Delay Budget
  • Relay UE determines 5QI for QoS control of Uu based on the implementation, and determines PQI for QoS control of PC5.
  • Relay UE puts the determined PQI, GFBR and MFBR in the acceptance message and sends it to Remote UE.
  • the PQI determined by the Relay UE may be different from the one sent by the Remote UE to the relay UE.
  • Relay UE can subsequently execute the PDU session modification process and request the network side to authorize the 5QI determined by Relay UE.
  • the communication connection establishment process based on L3relay can include the following steps:
  • Relay UE may establish a PDU session to relay future data before establishing a connection with Remote UE (remote terminal equipment).
  • Remote UE executes the discovery process to discover Relay UE that meets the requirements of Remote UE. In this process, Remote UE learns the connection services that Relay UE can provide.
  • the Remote UE selects a Relay UE and establishes a connection with the Relay UE. If there is no established PDU session that meets the requirements, the Relay UE initiates a new PDU session establishment process to the network before completing the PC5 connection establishment. When the network side determines that this session establishment is for relay data transmission, it initiates the establishment of QoS flow and the determination of QoS parameters. Remote UE can also initiate the establishment of QoS flow in this step by providing PC5QoS parameters to Relay UE, as described in the previous QoS processing chapter.
  • the corresponding IP address is assigned to the Remote UE.
  • the Remote UE may provide the QoS info of PC5 to the Relay UE in the Layer-2 (Layer 2, referred to as L2) link modification process.
  • the Relay UE determines the new QoS parameters based on the QoS info of PC5 and initiates the PDU session modification process. As described in the QoS handling chapter.
  • Relay UE sends a Remote UE report to SMF, including Remote User ID (ID of the remote terminal device) and Remote UE info (information of the remote terminal device).
  • Remote User ID identifies the UE that successfully established a connection in step S3.
  • Remote UE info is an auxiliary identifier used to identify the type of PDU session established through relay. For example, for an IP type PDU session, it is Remote UE IP info.
  • the server has strict requirements on the time it takes to perform AI operations. For example, when performing federated learning, there are strict requirements on the completion delay of each round to ensure the smooth progress of model training and faster convergence.
  • the server selects a UE as the execution node of the AI operation, it can send the delay requirement to the UE. This delay requirement includes the processing delay of the UE's local AI operation and the transmission time of sending the generated results to the server. extension.
  • the Relay UE does not know The time required for this AI operation. Therefore, it is impossible to perform QoS control on PC5 and Uu ports according to the existing mechanism, and thus there is no guarantee that Remote UE can still send AI operation results to the server on time when using Relay UE.
  • this application provides a wireless communication method that sends first information to the relay terminal device through the remote terminal device.
  • the relay terminal device determines the execution result of the target AI operation from the remote terminal device to the relay terminal device based on the first information.
  • the target AI operation is an AI operation completed by the cooperation of the two terminal devices, so that the relay terminal device can perform accurate QoS control based on the end-to-end transmission delay.
  • the relay-based mode In scenarios where AI operations are completed collaboratively, it is still possible to ensure that the AI operation results are sent to the server on time, improving reliability.
  • Latency 1 The delay required to complete an AI operation and send the result to the server, including the local processing delay of the UE and the transmission delay of sending the result to the server. At this time, the delay is delay 1, which means that the server has a Configuration requirements for AI operations.
  • Delay 2 The local processing delay that has been performed by the Remote UE before completing the connection establishment with the Relay UE.
  • Latency 4 After Relay UE receives the intermediate results sent by Remote UE, it still needs to process to complete the local processing delay required for AI local operations.
  • Remote UE is in the AI processing stage at delay 2. For example, a certain layer of the neural network has been trained locally, or the number of epochs that has been trained locally.
  • Parameter 2 The amount of intermediate data that Remote UE wants to send.
  • FIG. 9 shows a flow chart of a wireless communication method provided by an embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6. The method may include at least one of the following steps (910-930):
  • Step 910 The remote terminal device sends the first information to the relay terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation.
  • the relay terminal device receives the first information from the remote terminal device.
  • the first information is used to determine the end-to-end transmission delay corresponding to the execution result of the target AI operation for QoS control.
  • the end-to-end transmission delay refers to the transmission from the remote terminal device to the server. time delay.
  • the server may be a device that initiates the execution of the target AI operation.
  • the server may be an AI server or any other application server or business server, used to collect execution results of the target AI operation.
  • the target AI operation may be a model training operation, such as training a neural network model.
  • Step 920 The relay terminal device determines the end-to-end transmission delay corresponding to the execution result of the target AI operation based on the first information.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device to the server.
  • the end-to-end transmission delay is further calculated and determined by the relay terminal device based on information provided by the remote terminal device.
  • the first information includes information required for determining the end-to-end transmission delay.
  • the first information includes: execution progress information and first delay information.
  • the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation.
  • the first delay information is used to indicate the remaining time to complete the target AI operation. Extend the budget.
  • the relay terminal device can determine the end-to-end transmission delay based on the execution progress information and the first delay information.
  • the end-to-end transmission delay is determined by the remote terminal device, and the end-to-end transmission delay is directly indicated to the relay terminal device.
  • the first information includes the end-to-end transmission delay, and the relay terminal device can directly read the end-to-end transmission delay from the first information.
  • Step 930 The relay terminal device performs QoS control based on the end-to-end transmission delay.
  • the relay terminal device can perform QoS control on the first communication link and/or the second communication link according to the end-to-end transmission delay; where the first communication link refers to the remote terminal device
  • the second communication link refers to the communication link between the relay terminal equipment and the access network equipment. For example, the QoS parameters corresponding to the first communication link are determined, and/or the QoS parameters corresponding to the second communication link are determined.
  • the relay terminal device determines the amount of transmission data based on the end-to-end transmission delay, the amount of transmission data corresponding to the first communication link between the remote terminal device and the relay terminal device, the relay terminal device and the access network device.
  • the amount of transmitted data corresponding to the second communication link determines the first QoS parameter and the second QoS parameter; wherein the first QoS parameter refers to the QoS parameter corresponding to the first communication link, and the second QoS parameter refers to the second QoS parameter. 2.
  • the first QoS parameter includes but is not limited to at least one of the following: PQI, first GFBR, first MFBR.
  • the second QoS parameter includes but is not limited to at least one of the following: 5QI, second GFBR, and second MFBR.
  • the first QoS parameter can be understood as the QoS parameter corresponding to the PC5 interface, including PQI, GFBR, MFBR, etc.
  • the second QoS parameter can be understood as the QoS parameter corresponding to the Uu interface, including PQI, GFBR, MFBR, etc.
  • the first GFBR and the second GFBR are used in this application to distinguish; similarly, in order to distinguish the MFBRs corresponding to the PC5 interface and the Uu interface, the first MFBR and the second GFBR are used in this application. Two MFBRs are distinguished.
  • the first GFBR and the second GFBR determined by the relay terminal device may be the same or different.
  • the first MFBR and the second MFBR determined by the relay terminal device may be the same or different.
  • the relay terminal device can determine the corresponding QoS parameters based on the amount of data transmitted on the PC5 interface and the amount of data transmitted on the Uu interface respectively, to achieve precise and flexible control of QoS.
  • GFBR and MFBR are rate control parameters at the QoS flow level and are used for rate control of GBR type QoS flows.
  • GFBR instructs access network equipment (such as base stations) to ensure that sufficient resources are reserved for the code rate of a QoS stream transmission within the average time window.
  • MFBR is limited to the maximum bit rate of QoS stream transmission, and data exceeding MFBR may be discarded.
  • the access network equipment will schedule the data transmitted between GFBR and MFBR according to the scheduling priority corresponding to the 5QI of the QoS flow.
  • the relay terminal equipment can more accurately determine the QoS parameters on the PC5 and Uu ports based on the end-to-end transmission delay and the amount of data transmitted on the PC5 and Uu ports, thereby establishing an appropriate QoS flow.
  • the relevant data of the target AI operation is transmitted to the server to ensure the successful completion of the target AI operation.
  • the technical solution provided by the embodiment of the present application sends the first information to the relay terminal device through the remote terminal device, and the relay terminal device determines the execution result of the target AI operation based on the first information from the remote terminal device to the server.
  • the target AI operation is an AI operation completed by the cooperation of the two terminal devices, so that the relay terminal device can perform accurate QoS control based on the end-to-end transmission delay, and complete the AI operation in a relay-based manner.
  • it can ensure that the AI operation results are sent to the server on time it can ensure that the entire AI learning (such as federated learning) proceeds smoothly and improve the performance and speed of AI learning.
  • FIG. 10 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (1010-1040):
  • Step 1010 The remote terminal device sends first information to the relay terminal device.
  • the first information includes: execution progress information and first delay information.
  • the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation.
  • the first delay information is used to indicate the remaining delay budget to complete the target AI operation, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation.
  • the execution progress information includes a first parameter used to indicate an executed stage of the target AI operation by the remote terminal device.
  • the first parameter may be parameter 1 defined above.
  • the execution progress information includes a second parameter, which is used to indicate the amount of intermediate data related to the target AI operation that the remote terminal device needs to send to the relay terminal device.
  • the second parameter may be parameter 2 defined above.
  • the first delay information includes: a remaining delay budget for completing the target AI operation.
  • the first delay information includes the delay 3 defined above. In this way, the relay terminal device can directly read the remaining delay budget from the first delay information.
  • the first delay information includes: PQI corresponding to the remaining delay budget for completing the target AI operation.
  • the first delay information includes the PQI corresponding to the delay 3 defined above.
  • the relay terminal device can read the PQI corresponding to the remaining delay budget from the first delay information, and then determine the remaining delay budget based on the PQI, such as deriving or estimating the remaining delay budget based on the PQI.
  • Step 1020 The relay terminal device determines second delay information based on the above execution progress.
  • the second delay information is used to indicate the processing delay required by the relay terminal device to complete the remaining stages of the target AI operation.
  • the relay terminal device can determine the execution progress of the remote terminal device for the target AI operation based on the execution progress information, and then determine that the relay terminal device completes the target based on the execution progress and the local configuration of the relay terminal device.
  • the second delay information includes the delay 4 defined above.
  • the target AI operation includes performing 10 rounds of training on the target neural network.
  • the remote terminal device has performed 6 rounds of training on the target neural network.
  • the remote terminal device instructs the remote terminal by sending execution progress information to the relay terminal device.
  • the terminal device has performed 6 rounds of training on the target neural network, and the relay terminal device determines that it still needs to perform 4 rounds of training on the target neural network.
  • the relay terminal device determines based on its own local configuration (such as its own capability information, including (but not limited to computing power, etc.) estimates the time required to perform the above four rounds of training, and this time is the second delay information (or delay 4).
  • Step 1030 The relay terminal device determines the end-to-end transmission delay based on the first delay information and the second delay information.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device to the server.
  • Step 1040 The relay terminal device performs QoS control based on the end-to-end transmission delay.
  • step 1040 can be found in other embodiments mentioned above, and will not be described in detail in this embodiment.
  • a method of determining the end-to-end transmission delay is provided.
  • the remote terminal device provides its execution progress for the target AI operation and the remaining delay budget for completing the target AI operation to the relay terminal device.
  • the relay terminal device estimates the processing delay required to complete the remaining stages of the target AI operation, and then determines the end-to-end transmission delay, because the end-to-end transmission delay fully considers the respective requirements of the two terminal devices. Based on information such as processing capacity and capabilities, the determined end-to-end transmission delay is highly accurate, which in turn helps improve the accuracy of QoS control.
  • Figure 11 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (1110-1140):
  • Step 1110 The remote terminal device determines the end-to-end transmission delay based on the fourth delay information and the fifth delay information; wherein the fourth delay information is used to indicate the completion of the target AI operation and the execution result of the target AI operation. The total delay required to send to the server. The fifth delay information is used to indicate the processing delay required to complete the target AI operation.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device to the server. The terminal terminal device and the relay terminal device cooperate to complete the target AI operation.
  • the fourth delay information includes delay 1 as defined above, and the fifth delay information includes delay 5 as defined above.
  • the fourth delay information and the fifth delay information are specified by the server and provided to the remote terminal device.
  • the server determines the target AI operation, it stipulates in advance the total delay required to complete the target AI operation and send the execution results of the target AI operation to the server, as well as the processing delay required to complete the target AI operation.
  • Step 1120 The remote terminal device sends first information to the relay terminal device.
  • the first information includes: third delay information, and the third delay information is used to indicate the end-to-end transmission delay.
  • the remote terminal device after determining the end-to-end transmission delay, the remote terminal device sends the end-to-end transmission delay to the relay terminal device.
  • the first information also includes: execution progress information and second delay information, the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation, and the second delay information is used to indicate the relay The processing delay required by the terminal device to complete the remaining stages of the target AI operation.
  • the execution progress information includes a first parameter used to indicate an executed stage of the target AI operation by the remote terminal device.
  • the first parameter may be parameter 1 defined above.
  • the execution progress information includes a second parameter, which is used to indicate the amount of intermediate data related to the target AI operation that the remote terminal device needs to send to the relay terminal device.
  • the second parameter may be parameter 2 defined above.
  • the second delay information includes delay 4 as defined above.
  • the remote terminal device determines the second delay information based on the fifth delay information and the sixth delay information; wherein the sixth delay information is used to indicate the processed delay of the remote terminal device for the target AI operation.
  • the fifth delay information includes the delay 5 defined above
  • the sixth delay information includes the delay 2 defined above.
  • Step 1130 The relay terminal device determines the end-to-end transmission delay based on the third delay information.
  • the relay terminal device may determine the end-to-end transmission delay based on the received third delay information.
  • Step 1140 The relay terminal device performs QoS control based on the end-to-end transmission delay.
  • step 1140 please refer to other embodiments mentioned above, and will not be described in detail in this embodiment.
  • the relay terminal device may also perform the following steps: the relay terminal device performs the target AI operation according to the execution of the remote terminal device progress, determine the remaining stages of the target AI operation, and execute the remaining stages of the target AI operation based on the second delay information.
  • the relay terminal device can determine the processing delay required by itself to complete the remaining stages of the target AI operation based on the second delay information, and then combine the determined remaining stages of the target AI operation, thereby knowing that the relay terminal equipment How long does it take to complete the remaining stage of the target AI operation, so as to use appropriate computing power and other configurations to execute the remaining stage of the target AI operation and ensure that the remaining stage of the target AI operation can be completed within the time indicated by the above-mentioned second delay information? Completed within the time delay requirement.
  • the remote terminal device determines the total delay configured, defined or specified in advance and the processing delay required to complete the target AI operation.
  • the end-to-end transmission delay is determined, and the determined end-to-end transmission delay satisfies the above configuration, definition or regulation, thereby helping to improve the accuracy of QoS control.
  • the remote terminal device sends the first information to the relay terminal device through a connection establishment request.
  • the remote terminal device sends a connection establishment request to the relay terminal device.
  • the connection establishment request is used to request the establishment of a first communication link between the remote terminal device and the relay terminal device.
  • the connection establishment request includes first information.
  • the relay terminal device receives the connection establishment request from the remote terminal device.
  • the relay terminal device may establish a first communication link between the remote terminal device and the relay terminal device, and then send a connection establishment response to the remote terminal device,
  • the connection establishment response is used to indicate that the relay terminal device agrees to establish the first communication link.
  • the connection establishment response includes QoS parameters corresponding to the first communication link.
  • the relay terminal device determines the end-to-end transmission delay described in the above embodiment based on the first information included in the connection establishment request, and then determines the QoS corresponding to the first communication link based on the end-to-end transmission delay. parameters, and carry the QoS parameters corresponding to the first communication link in the connection establishment response and send it to the remote terminal device.
  • the first information and QoS parameters are exchanged during the connection establishment process, and the establishment of the QoS flow can be completed faster, ensuring that the remote terminal device transmits the relevant data of the target AI operation to the relay terminal device in a timely manner, thereby smoothly Complete AI operation.
  • the remote terminal device sends the first information to the relay terminal device through a link modification request.
  • the remote terminal device sends a link modification request to the relay terminal device.
  • the link modification request is used to request modification of the first communication link that has been established between the remote terminal device and the relay terminal device.
  • the link modification request Includes first message.
  • the relay terminal device receives the link modification request from the remote terminal device.
  • the relay terminal device may confirm whether it agrees to modify the first communication link, and then send a link modification response to the remote terminal device, where the link modification response is used. Instruct the relay terminal device to agree to modify the first communication link.
  • the link modification response includes QoS parameters corresponding to the first communication link.
  • the relay terminal device determines the end-to-end transmission delay described in the above embodiment based on the first information included in the link modification request, and then determines the end-to-end transmission delay corresponding to the first communication link based on the end-to-end transmission delay.
  • QoS parameters, and the QoS parameters corresponding to the first communication link are carried in the link modification response and sent to the remote terminal device.
  • a method of exchanging the first information and QoS parameters in the link modification process is provided, that is, triggering the L2 link modification process on PC5 to complete the establishment of a QoS flow that meets the requirements.
  • the timeliness of completing the QoS flow establishment during the connection establishment process will be relatively poor, but it provides another alternative method.
  • these two methods can be used alone or in combination.
  • the first information and QoS parameters can be exchanged during the connection establishment process to make it faster. Complete the establishment of the QoS flow as quickly as possible; when the PC5 connection has been established or when the demand for immediacy is not high, the establishment of the QoS flow that meets the requirements is completed by exchanging the first information and QoS parameters in the link modification process.
  • the relay terminal device may also send QoS parameters corresponding to the second communication link between the relay terminal device and the access network device to the core network element. For example, according to the end-to-end transmission delay of the relay terminal device, combined with the amount of transmission data corresponding to the first communication link between the remote terminal device and the relay terminal device, the amount of data transmitted between the relay terminal device and the access network device. The amount of transmitted data corresponding to the second communication link is determined, the QoS parameters corresponding to the second communication link between the relay terminal equipment and the access network equipment are determined, and then the QoS parameters are sent to the core network element.
  • the QoS parameters corresponding to the second communication link are sent through the PDU session modification process.
  • the relay terminal device sends a PDU session modification request to the core network element, and the PDU session modification request includes the QoS parameters corresponding to the second communication link.
  • the QoS parameters corresponding to the second communication link are sent to the core network element, so that a QoS flow that meets the requirements can be established between the relay terminal device and the core network element, ensuring that the relay terminal device delivers the target AI in a timely manner.
  • the relevant data of the operation is passed to the core network element and sent to the server using the core network element to successfully complete the AI operation.
  • Figure 12 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (A1-A8):
  • Relay UE may establish a PDU session to relay future data before establishing a connection with Remote UE.
  • Remote UE executes the discovery process to discover Relay UE that meets the requirements of Remote UE. In this process, Remote UE learns the connection services that Relay UE can provide.
  • Remote UE selects a Relay UE and sends a communication connection establishment request.
  • the request includes delay 3 and parameter 1 or 2.
  • Remote UE can send delay 3 as a separate parameter to Relay UE, or it can send a request that meets Required PQI. For example, delay 3 is mapped to a PDB that is equal to or similar to its PQI, so that there is no need to introduce new parameters (i.e. delay 3).
  • Relay UE estimates delay 4 based on parameters 1 or 2 and local configuration. Based on delay 3 or the corresponding PDB in PQI, the end-to-end transmission delay required for the AI operation result is obtained, that is, from Remote UE to The transmission delay required by the final server.
  • Relay UE cannot set the GFBR and MFBR in the QoS parameters corresponding to the PC5 and Uu interfaces to be the same according to the existing mechanism.
  • Relay UE is based on parameter 1 or 2 and the data size of the result after executing the AI operation. It knows the data size that needs to be transmitted on PC5 and Uu, and based on the end-to-end transmission delay and the amount of data that needs to be transmitted on each interface. , to determine the QoS parameters of the PC5 and Uu interfaces, including PQI, GFBR, and MFBR on the PC5 interface, and 5QI, GFBR, and MFBR on the Uu interface. The GFBR and MFBR on the PC5 interface and the Uu interface can be different.
  • Relay UE sends the determined QoS parameters on the PC5 interface to Remote UE in the communication acceptance message, including PQI, GFBR and MFBR.
  • IP address is assigned to the Remote UE.
  • the link establishment between Remote UE and Relay UE has been completed, and Remote UE can send intermediate data to Relay UE. Therefore, through the method of this embodiment, by sending delay 3 and parameter 1 or 2 in the connection establishment process, the intermediate data can be sent to Relay as quickly as possible when the UE is about to run out of power or is about to move outside the coverage area. UE.
  • Relay UE initiates the PDU session modification process based on the QoS parameters on the Uu interface determined in step A4, and establishes a qualified QoS flow on the Uu interface.
  • Relay UE sends a Remote UE report to SMF, including Remote User ID and Remote UE info.
  • Remote User ID identifies the UE that successfully established the connection in step A3.
  • Remote UE info is an auxiliary identifier used to identify the type of PDU session established through relay. For example, for an IP type PDU session, it is Remote UE IP info.
  • the application layer configures delay 1 to the Remote UE.
  • parameter 1, parameter 2 and delay 2 can be obtained.
  • delay 3 is calculated.
  • Remote UE sends delay 3, parameter 1 or parameter 2 to Relay UE.
  • Relay UE estimates the delay 4 based on parameter 1 or parameter 2 and local configuration (such as some local capabilities, such as the number of processor cores and other computing power).
  • the AI operation result needs to be obtained
  • the end-to-end transmission delay is the transmission delay required from the Remote UE to the final server.
  • Figure 13 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (B1 to B8):
  • Relay UE may establish a PDU session to relay future data before establishing a connection with Remote UE.
  • Remote UE executes the discovery process to discover Relay UE that meets the requirements of Remote UE. In this process, Remote UE learns the connection services that Relay UE can provide.
  • the Remote UE selects a Relay UE and establishes a connection with the Relay UE. If there is no established PDU session that meets the requirements, the Relay UE initiates a new PDU session establishment process to the network before completing the PC5 connection establishment. When the network side determines that this session establishment is for relay data transmission, it initiates the establishment of QoS flow and the determination of QoS parameters. Remote UE can also initiate the establishment of QoS flow in this step by providing PC5QoS parameters to Relay UE, as described in the previous QoS processing chapter.
  • the corresponding IP address is assigned to the Remote UE.
  • Remote UE sends a link modification request.
  • the request includes delay 3 and parameter 1 or 2.
  • the Remote UE can send the delay 3 to the Relay UE as a separate parameter, or by sending a PQI that meets the requirements, for example, mapping the delay 3 to a PDB that is equal to or similar to the PQI.
  • Relay UE estimates delay 4 based on parameter 1 or 2 and local configuration. Based on delay 3 or the corresponding PDB in PQI, the end-to-end transmission delay required for the AI operation result is obtained, that is, from Remote UE to The transmission delay required by the final server.
  • Relay UE cannot set the GFBR and MFBR in the QoS parameters corresponding to the PC5 and Uu interfaces to be the same according to the existing mechanism.
  • Relay UE is based on parameter 1 or 2 and the data size of the result after executing the AI operation. It knows the data size that needs to be transmitted on PC5 and Uu, and based on the end-to-end transmission delay and the amount of data that needs to be transmitted on each interface. , to determine the QoS parameters of the PC5 and Uu interfaces, including PQI, GFBR, and MFBR on the PC5 interface, and 5QI, GFBR, and MFBR on the Uu interface. The GFBR and MFBR on the PC5 interface and the Uu interface can be different.
  • Relay UE initiates a PDU session modification request, carrying the QoS parameters of the Uu port determined by Relay UE, to establish a qualified QoS flow on Uu.
  • Relay UE sends a link modification acceptance message, carrying the PC5QoS parameters determined by Relay UE in the message.
  • Relay UE sends a Remote UE report to SMF, including Remote User ID and Remote UE info.
  • Remote User ID identifies the UE that successfully established the connection in step B3.
  • Remote UE info is an auxiliary identifier used to identify the type of PDU session established through relay. For example, for an IP type PDU session, it is Remote UE IP info.
  • the Relay UE since the relevant parameters are transferred in the link modification process, the Relay UE can accurately determine the QoS parameters on PC5 and Uu. Therefore, after step B7 is completed, the Remote UE can send the intermediate data to the Relay UE. Slightly slower than the embodiment shown in Figure 12.
  • Figure 14 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (C1-C8):
  • Relay UE may establish a PDU session to relay future data before establishing a connection with Remote UE.
  • Remote UE executes the discovery process to discover Relay UE that meets the requirements of Remote UE. In this process, Remote UE learns the connection services that Relay UE can provide.
  • Remote UE selects a Relay UE and sends a communication connection establishment request.
  • the request includes end-to-end transmission delay, delay 4 and parameter 2.
  • the AI server specifies delay 1 and delay 5, that is, the local processing delay, and configures these parameters to the remote UE.
  • Remote UE can obtain the end-to-end transmission delay through delay 1-delay 5.
  • Relay UE reads the end-to-end transmission delay, delay 4 and parameter 2 from the communication connection establishment request, and performs AI operations based on delay 4 and parameter 2 to complete the remaining stages of processing.
  • the Relay UE determines the QoS parameters of the PC5 and Uu interfaces based on the end-to-end transmission delay and the amount of data that needs to be transmitted on the PC5 and Uu interfaces respectively, as described in the embodiments of Figures 12 and 13 above.
  • Relay UE sends the determined QoS parameters on the PC5 interface to the Remote UE in the communication acceptance message, including PQI, GFBR and MFBR.
  • the corresponding IP address is assigned to the Remote UE.
  • Relay UE initiates the PDU session modification process based on the QoS parameters on the Uu interface determined in step C4, and establishes a qualified QoS flow on the Uu interface.
  • Relay UE sends a Remote UE report to SMF, including Remote User ID and Remote UE info.
  • Remote User ID identifies the UE that successfully established the connection in step C3.
  • Remote UE info is an auxiliary identifier used to identify the type of PDU session established through relay. For example, for an IP type PDU session, it is Remote UE IP info.
  • Figure 15 shows a flow chart of a wireless communication method provided by another embodiment of the present application. This method can be applied to the network architecture shown in Figure 1 or Figure 6.
  • the method may include at least one of the following steps (D1 to D8):
  • Relay UE may establish a PDU session to relay future data before establishing a connection with Remote UE.
  • Remote UE executes the discovery process to discover Relay UE that meets the requirements of Remote UE. In this process, Remote UE learns the connection services that Relay UE can provide.
  • the Remote UE selects a Relay UE and establishes a connection with the Relay UE. If there is no established PDU session that meets the requirements, the Relay UE initiates a new PDU session establishment process to the network before completing the PC5 connection establishment. When the network side determines that this session establishment is for relay data transmission, it initiates the establishment of QoS flow and the determination of QoS parameters. Remote UE can also initiate the establishment of QoS flow in this step by providing PC5QoS parameters to Relay UE, as described in the previous QoS processing chapter.
  • the corresponding IP address is assigned to the Remote UE.
  • Remote UE sends a link modification request.
  • the request includes end-to-end transmission delay, delay 4 and parameter 2.
  • the AI server specifies delay 1 and delay 5, that is, the local processing delay, and configures these parameters to the remote UE.
  • Remote UE can obtain the end-to-end transmission delay through delay 1-delay 5.
  • Relay UE reads the end-to-end transmission delay, delay 4 and parameter 2 from the link modification request, and performs AI operations based on delay 4 and parameter 2 to complete the remaining stages of processing.
  • the Relay UE determines the QoS parameters of the PC5 and Uu interfaces based on the end-to-end transmission delay and the amount of data that needs to be transmitted on the PC5 and Uu interfaces respectively, as described in the embodiments of Figures 12 and 13 above.
  • Relay UE initiates a PDU session modification request, carrying the QoS parameters of the Uu port determined by Relay UE, to establish a qualified QoS flow on Uu.
  • Relay UE sends a link modification acceptance message, carrying the PC5QoS parameters determined by Relay UE in the message.
  • Relay UE sends a Remote UE report to SMF, including Remote User ID and Remote UE info.
  • Remote User ID identifies the UE that successfully established the connection in step D3.
  • Remote UE info is an auxiliary identifier used to identify the type of PDU session established through relay. For example, for an IP type PDU session, it is Remote UE IP info.
  • FIG. 16 shows a block diagram of a wireless communication device provided by an embodiment of the present application.
  • the device has the function of realizing the above method example executed by the relay terminal equipment.
  • the function can be realized by hardware, or can also be realized by hardware executing corresponding software.
  • the device may be a relay terminal equipment, or may be provided in the relay terminal equipment.
  • the device 1600 may include: a receiving module 1610, a determining module 1620 and a control module 1630.
  • the receiving module 1610 is used to receive the first information from the remote terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation.
  • the determination module 1620 is configured to determine, based on the first information, the end-to-end transmission delay corresponding to the execution result of the target AI operation.
  • the end-to-end transmission delay refers to the time from the remote terminal device to Server transmission delay.
  • the control module 1630 is used to perform QoS control according to the end-to-end transmission delay.
  • the first information includes: execution progress information and first delay information, the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation, and the third A delay information is used to indicate the remaining delay budget to complete the target AI operation.
  • the determination module 1620 is configured to determine second delay information according to the execution progress. The second delay information is used to indicate the processing time required for the relay terminal device to complete the remaining stages of the target AI operation. Delay; determine the end-to-end transmission delay according to the first delay information and the second delay information.
  • the first delay information includes: the remaining delay budget; or the PQI corresponding to the remaining delay budget.
  • the first information includes: third delay information, the third delay information is used to indicate the end-to-end transmission delay.
  • the end-to-end transmission delay is determined by the remote terminal device based on fourth delay information and fifth delay information; wherein the fourth delay information is used to indicate completion of the The total delay required to perform a target AI operation and send the execution result of the target AI operation to the server, and the fifth delay information is used to indicate the processing delay required to complete the target AI operation.
  • the fourth delay information and the fifth delay information are specified by the server and provided to the remote terminal device.
  • the first information further includes: execution progress information and second delay information.
  • the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation.
  • the second delay information is used to indicate the processing delay required by the relay terminal device to complete the remaining stages of the target AI operation.
  • the device 1600 further includes: an execution module 1640, configured to determine the remaining stages of the target AI operation according to the execution progress; and execute the target AI operation according to the second delay information. remaining stages.
  • the execution progress information includes: a first parameter used to indicate the executed stage of the target AI operation by the remote terminal device; or a second parameter used to indicate the remote terminal device The amount of intermediate data related to the target AI operation that the terminal device needs to send to the relay terminal device.
  • control module 1630 is configured to determine the end-to-end transmission delay and the amount of transmission data corresponding to the first communication link between the remote terminal device and the relay terminal device. , the transmission data amount corresponding to the second communication link between the relay terminal equipment and the access network equipment, determine the first QoS parameter and the second QoS parameter; wherein the first QoS parameter refers to the third QoS parameter.
  • the first QoS parameter includes at least one of the following: PQI, first GFBR, first MFBR.
  • the second QoS parameter includes at least one of the following: 5QI, second GFBR, and second MFBR.
  • the receiving module 1610 is used to receive a connection establishment request from the remote terminal device, where the connection establishment request is used to request the establishment of a connection between the remote terminal device and the relay terminal device.
  • the first communication link between the two parties, the connection establishment request includes the first information.
  • the apparatus 1600 further includes: a sending module 1650, configured to send a connection establishment response to the remote terminal device, where the connection establishment response is used to indicate to the relay terminal The device agrees to establish the first communication link, and the connection establishment response includes QoS parameters corresponding to the first communication link.
  • a sending module 1650 configured to send a connection establishment response to the remote terminal device, where the connection establishment response is used to indicate to the relay terminal The device agrees to establish the first communication link, and the connection establishment response includes QoS parameters corresponding to the first communication link.
  • the receiving module 1610 is used to receive a link modification request from the remote terminal device.
  • the link modification request is used to request modification of the remote terminal device and the relay terminal.
  • a first communication link has been established between devices, and the link modification request includes the first information.
  • the apparatus 1600 further includes: a sending module 1650, configured to send a link modification response to the remote terminal device, where the link modification response is used to indicate that the After the terminal device agrees to modify the first communication link, the link modification response includes QoS parameters corresponding to the first communication link.
  • a sending module 1650 configured to send a link modification response to the remote terminal device, where the link modification response is used to indicate that the After the terminal device agrees to modify the first communication link, the link modification response includes QoS parameters corresponding to the first communication link.
  • the apparatus 1600 further includes: a sending module 1650, configured to send the second communication link between the relay terminal equipment and the access network equipment to the core network element. Corresponding QoS parameters.
  • the QoS parameters corresponding to the second communication link are sent through a PDU session modification process.
  • FIG. 17 shows a block diagram of a wireless communication device provided by another embodiment of the present application.
  • the device has the function of implementing the above method example executed by the remote terminal device.
  • the function may be implemented by hardware, or may be implemented by hardware executing corresponding software.
  • the device may be a remote terminal device, or may be provided in the remote terminal device.
  • the device 1700 may include: a sending module 1710.
  • the sending module 1710 is used to send the first information to the relay terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation.
  • the first information is used to determine the end-to-end transmission delay corresponding to the execution result of the target AI operation for QoS control.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device. Transmission delay to the server.
  • the first information includes: execution progress information and first delay information
  • the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation
  • the third A delay information is used to indicate the remaining delay budget to complete the target AI operation.
  • the end-to-end transmission delay is determined by the relay terminal device according to the first delay information and the second delay information
  • the second delay information is determined according to the execution progress
  • the third delay information is determined according to the execution progress.
  • the second delay information is used to indicate the processing delay required by the relay terminal device to complete the remaining stages of the target AI operation.
  • the first delay information includes: the remaining delay budget; or the PQI corresponding to the remaining delay budget.
  • the first information includes: third delay information, the third delay information is used to indicate the end-to-end transmission delay.
  • the device 1700 further includes: a determining module 1720, configured to determine the end-to-end transmission delay according to the fourth delay information and the fifth delay information; wherein, The fourth delay information is used to indicate the total delay required to complete the target AI operation and send the execution result of the target AI operation to the server, and the fifth delay information is used to indicate the completion of the target AI operation. Describe the processing delay required for the target AI operation.
  • the fourth delay information and the fifth delay information are specified by the server and provided to the remote terminal device.
  • the first information further includes: execution progress information and second delay information.
  • the execution progress information is used to indicate the execution progress of the remote terminal device for the target AI operation.
  • the second delay information is used to indicate the processing delay required by the relay terminal device to complete the remaining stages of the target AI operation.
  • the execution progress information includes: a first parameter used to indicate the executed stage of the target AI operation by the remote terminal device; or a second parameter used to indicate the remote terminal device The amount of intermediate data related to the target AI operation that the terminal device needs to send to the relay terminal device.
  • the end-to-end transmission delay is used to determine the first QoS parameter and the second QoS parameter; wherein the first QoS parameter refers to the remote terminal device and the relay terminal device.
  • the QoS parameters corresponding to the first communication link between the relay terminal equipment and the access network equipment, and the second QoS parameters refer to the QoS parameters corresponding to the second communication link between the relay terminal equipment and the access network equipment.
  • the first QoS parameter includes at least one of the following: PQI, first GFBR, first MFBR.
  • the second QoS parameter includes at least one of the following: 5QI, second GFBR, and second MFBR.
  • the sending module 1710 is used to send a connection establishment request to the relay terminal device, where the connection establishment request is used to request the establishment of a connection between the remote terminal device and the relay terminal device.
  • the first communication link, the connection establishment request includes the first information.
  • the apparatus 1700 further includes: a receiving module 1730, configured to receive a connection establishment response from the relay terminal device, where the connection establishment response is used to indicate to the relay The terminal device agrees to establish the first communication link, and the connection establishment response includes QoS parameters corresponding to the first communication link.
  • the sending module 1710 is used to send a link modification request to the relay terminal device, where the link modification request is used to request modification of the remote terminal device and the relay terminal device.
  • the first communication link has been established between the two parties, and the link modification request includes the first information.
  • the apparatus 1700 further includes: a receiving module 1730, configured to receive a link modification response from the relay terminal device, where the link modification response is used to indicate that the The relay terminal device agrees to modify the first communication link, and the link modification response includes QoS parameters corresponding to the first communication link.
  • the device provided in the above embodiment implements its functions, only the division of the above functional modules is used as an example. In actual applications, the above function allocation can be completed by different functional modules according to actual needs. That is, the content structure of the device is divided into different functional modules to complete all or part of the functions described above.
  • the terminal device 1800 may include: a processor 1801, a transceiver 1802, and a memory 1803.
  • the processor 1801 includes one or more processing cores.
  • the processor 1801 executes various functional applications and information processing by running software programs and modules.
  • the transceiver 1802 may include a receiver and a transmitter.
  • the receiver and the transmitter may be implemented as the same wireless communication component, and the wireless communication component may include a wireless communication chip and a radio frequency antenna.
  • Memory 1803 may be connected to processor 1801 and transceiver 1802.
  • the memory 1803 can be used to store a computer program executed by the processor, and the processor 1801 is used to execute the computer program to implement various steps executed by the remote terminal device or the relay terminal device in the above method embodiment.
  • memory 1803 may be implemented by any type of volatile or non-volatile storage device, or combination thereof, including but not limited to: magnetic or optical disks, electrically erasable programmable Read-only memory, erasable programmable read-only memory, static ready-access memory, read-only memory, magnetic memory, flash memory, programmable read-only memory.
  • the terminal device 1800 when the terminal device 1800 is the relay terminal device introduced in the above embodiment,
  • the transceiver 1802 is used to receive the first information from a remote terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation;
  • the processor 1801 is configured to determine, based on the first information, the end-to-end transmission delay corresponding to the execution result of the target AI operation.
  • the end-to-end transmission delay refers to the transmission time from the remote terminal to the remote terminal.
  • the terminal device 1800 when the terminal device 1800 is the remote terminal device introduced in the above embodiment,
  • the transceiver 1802 is used to send first information to a relay terminal device, and the remote terminal device and the relay terminal device cooperate to complete the target AI operation; wherein the first information is used to determine the target
  • the end-to-end transmission delay corresponding to the execution result of the AI operation is used for QoS control.
  • the end-to-end transmission delay refers to the transmission delay from the remote terminal device to the server.
  • Embodiments of the present application also provide a computer-readable storage medium.
  • a computer program is stored in the storage medium.
  • the computer program is used to be executed by a processor of the relay terminal device to implement the execution of the above-mentioned relay terminal device. wireless communication method.
  • Embodiments of the present application also provide a computer-readable storage medium.
  • a computer program is stored in the storage medium.
  • the computer program is used to be executed by a processor of a remote terminal device to implement the above execution of the remote terminal device. wireless communication method.
  • the computer-readable storage medium may include: ROM (Read-Only Memory), RAM (Random-Access Memory), SSD (Solid State Drives, solid state drive) or optical disk, etc. .
  • random access memory can include ReRAM (Resistance Random Access Memory, resistive random access memory) and DRAM (Dynamic Random Access Memory, dynamic random access memory).
  • Embodiments of the present application also provide a chip, which includes programmable logic circuits and/or program instructions. When the chip is run on a relay terminal device, it is used to implement the wireless operation performed by the relay terminal device. Communication methods.
  • Embodiments of the present application also provide a chip.
  • the chip includes programmable logic circuits and/or program instructions. When the chip is run on a remote terminal device, it is used to implement the wireless operation performed by the remote terminal device. Communication methods.
  • Embodiments of the present application also provide a computer program product.
  • the computer program product includes computer instructions.
  • the computer instructions are stored in a computer-readable storage medium.
  • the processor of the relay terminal device obtains the information from the computer-readable storage medium. Read and execute the computer instructions to implement the wireless communication method executed by the above relay terminal device.
  • Embodiments of the present application also provide a computer program product.
  • the computer program product includes computer instructions.
  • the computer instructions are stored in a computer-readable storage medium.
  • the processor of the remote terminal device obtains the instructions from the computer-readable storage medium. Read and execute the computer instructions to implement the wireless communication method executed by the remote terminal device.
  • the "instruction” mentioned in the embodiments of this application may be a direct instruction, an indirect instruction, or an association relationship.
  • a indicates B which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, and B can be obtained through C; it can also mean that there is an association between A and B. relation.
  • correlate can mean that there is a direct correspondence or indirect correspondence between the two, it can also mean that there is an associated relationship between the two, or it can mean indicating and being instructed, configuration and being. Configuration and other relationships.
  • predefined can be realized by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the equipment (for example, including terminal equipment and core network elements).
  • the application does not limit its specific implementation method.
  • predefined can refer to what is defined in the protocol.
  • the "protocol” may refer to a standard protocol in the communication field, which may include, for example, LTE protocol, NR protocol, and related protocols applied in future communication systems. This application is not limited to this.
  • the "plurality” mentioned in this article means two or more than two.
  • “And/or” describes the relationship between related objects, indicating that there can be three relationships.
  • a and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone.
  • the character “/” generally indicates that the related objects are in an "or” relationship.
  • step numbers described in this article only illustrate a possible execution sequence between the steps.
  • the above steps may not be executed in the numbering sequence, such as two different numbers.
  • the steps are executed simultaneously, or two steps with different numbers are executed in the reverse order as shown in the figure, which is not limited in the embodiments of the present application.
  • Computer-readable media includes computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another.
  • Storage media can be any available media that can be accessed by a general purpose or special purpose computer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种无线通信方法、装置、设备、存储介质及程序产品，涉及通信技术领域。上述方法包括：远端终端设备向中继终端设备发送第一信息，该第一信息用于确定目标AI操作的执行结果所对应的端到端传输时延(910)；中继终端设备根据第一信息，确定目标AI操作的执行结果所对应的端到端传输时延，端到端传输时延是指从远端终端设备到服务器的传输时延(920)；中继终端设备根据端到端传输时延进行QoS控制(930)。通过上述方法，使得中继终端设备能够根据该端到端传输时延进行准确的QoS控制，在基于中继方式合作完成AI操作的场景下，仍然可以保证将AI操作结果按时发送到服务器，提升可靠性。

Description

无线通信方法、装置、设备、存储介质及程序产品 技术领域
本申请实施例涉及通信技术领域，特别涉及一种无线通信方法、装置、设备、存储介质及程序产品。
背景技术
随着终端设备(如移动终端)上的摄像头和传感器性能的不断提高，越来越多的终端设备可以收集对AI(Artificial Intelligence，人工智能)或ML(Machine Learning，机器学习)模型训练必不可少的有价值的训练数据。对于许多AI或ML任务，终端设备收集的小样本数据对于训练全局模型具有重要的意义。
以联邦学习场景为例，FL(Federated Learning，联邦学习)服务器通过聚合各个终端设备上报的局部训练结果来完成全局模型的训练。随着技术的演进，提出了借助Prose(Proximity-based Services，近距离通信业务/邻近业务)方式的机器学习架构。仍然以联邦学习场景为例，当参与联邦学习的某一终端设备因某些原因无法完成整个本地训练时，可以借助Prose的方式，将模型训练的中间结果发送给其它终端设备，由其它终端设备完成后续的计算。
针对借助Prose方式的机器学习架构，如何保证AI操作的顺利完成，还需进一步研究。
发明内容
本申请实施例提供了一种无线通信方法、装置、设备、存储介质及程序产品。所述技术方案如下：
根据本申请实施例的一个方面，提供了一种无线通信方法，所述方法由中继终端设备执行，所述方法包括：
接收来自远端终端设备的第一信息，所述远端终端设备和所述中继终端设备合作完成目标AI操作；
根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延；
根据所述端到端传输时延进行QoS(Quality of Service，服务质量)控制。
根据本申请实施例的一个方面，提供了一种无线通信方法，所述方法由远端终端设备执行，所述方法包括：
向中继终端设备发送第一信息，所述远端终端设备和所述中继终端设备合作完成目标AI操作；
其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
根据本申请实施例的一个方面，提供了一种无线通信装置，所述装置包括：
接收模块，用于接收来自远端终端设备的第一信息，所述远端终端设备和中继终端设备合作完成目标AI操作；
确定模块，用于根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延；
控制模块，用于根据所述端到端传输时延进行QoS控制。
根据本申请实施例的一个方面，提供了一种无线通信装置，所述装置包括：
发送模块，用于向中继终端设备发送第一信息，远端终端设备和所述中继终端设备合作完成目标AI操作；
其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
根据本申请实施例的一个方面，提供了一种终端设备，所述终端设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述计算机程序以实现上述中继终端设备或远端终端设备所执行的无线通信方法。
根据本申请实施例的一个方面，提供了一种计算机可读存储介质，所述存储介质中存储有计算机程序，所述计算机程序用于被处理器执行，以实现上述中继终端设备或远端终端设备所执行的无线通信方法。
根据本申请实施例的一个方面，提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片运行时，用于实现上述中继终端设备或远端终端设备所执行的无线通信方法。
根据本申请实施例的一个方面，提供了一种计算机程序产品，所述计算机程序产品包括计算机指令， 所述计算机指令存储在计算机可读存储介质中，处理器从所述计算机可读存储介质读取并执行所述计算机指令，以实现上述中继终端设备或远端终端设备所执行的无线通信方法。
本申请实施例提供的技术方案可以包括如下有益效果：
通过远端终端设备向中继终端设备发送第一信息，中继终端设备根据该第一信息确定目标AI操作的执行结果从远端终端设备到服务器的端到端传输时延，该目标AI操作是这两个终端设备合作完成的AI操作，使得中继终端设备能够根据该端到端传输时延进行准确的QoS控制，在基于中继方式合作完成AI操作的场景下，仍然可以保证将AI操作结果按时发送到服务器，提升可靠性。
附图说明
图1是本申请一个实施例提供的网络架构的示意图；
图2是本申请另一个实施例提供的网络架构的示意图；
图3是本申请另一个实施例提供的网络架构的示意图；
图4是本申请一个实施例提供的联邦学习架构的示意图；
图5是本申请一个实施例提供的借助Prose方式的联邦学习架构的示意图；
图6是本申请一个实施例提供的Prose架构的示意图；
图7是本申请一个实施例提供的Prose架构下的QoS处理的示意图；
图8是本申请一个实施例提供的基于中继的通信连接建立流程的示意图；
图9是本申请一个实施例提供的无线通信方法的流程图；
图10是本申请另一个实施例提供的无线通信方法的流程图；
图11是本申请另一个实施例提供的无线通信方法的流程图；
图12是本申请另一个实施例提供的无线通信方法的流程图；
图13是本申请另一个实施例提供的无线通信方法的流程图；
图14是本申请另一个实施例提供的无线通信方法的流程图；
图15是本申请另一个实施例提供的无线通信方法的流程图；
图16是本申请一个实施例提供的无线通信装置的框图；
图17是本申请另一个实施例提供的无线通信装置的框图；
图18是本申请一个实施例提供的终端设备的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
本申请实施例描述的网络架构以及业务场景是为了更加清楚地说明本申请实施例的技术方案，并不构成对本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着网络架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
本申请实施例的技术方案可以应用于各种通信系统，例如：全球移动通讯(Global System of Mobile communication，GSM)系统、码分多址(Code Division Multiple Access，CDMA)系统、宽带码分多址(Wideband Code Division Multiple Access，WCDMA)系统、通用分组无线业务(General Packet Radio Service，GPRS)、长期演进(Long Term Evolution，LTE)系统、先进的长期演进(Advanced long term evolution，LTE-A)系统、新无线(New Radio，NR)系统、NR系统的演进系统、非授权频谱上的LTE(LTE-based access to unlicensed spectrum，LTE-U)系统、非授权频谱上的NR(NR-based access to unlicensed spectrum，NR-U)系统、非地面通信网络(Non-Terrestrial Networks，NTN)系统、通用移动通信系统(Universal Mobile Telecommunication System，UMTS)、无线局域网(Wireless Local Area Networks，WLAN)、无线保真(Wireless Fidelity，WiFi)、第五代通信系统或其他通信系统等。
通常来说，传统的通信系统支持的连接数有限，也易于实现，然而，随着通信技术的发展，移动通信系统将不仅支持传统的通信，还将支持例如，设备到设备(Device to Device，D2D)通信，机器到机器(Machine to Machine，M2M)通信，机器类型通信(Machine Type Communication，MTC)，车辆间(Vehicle to Vehicle，V2V)通信，或车联网(Vehicle to everything，V2X)通信等，本申请实施例也可以应用于这些通信系统。
本申请实施例中的通信系统可以应用于载波聚合(Carrier Aggregation，CA)场景，也可以应用于双连接(Dual Connectivity，DC)场景，还可以应用于独立(Standalone，SA)布网场景。
本申请实施例中的通信系统可以应用于非授权频谱，其中，非授权频谱也可以认为是共享频谱；或者，本申请实施例中的通信系统也可以应用于授权频谱，其中，授权频谱也可以认为是非共享频谱。
本申请实施例可应用于非地面通信网络(Non-Terrestrial Networks，NTN)系统，也可应用于地面通信 网络(Terrestrial Networks，TN)系统。
请参考图1，其示出了本申请一个实施例提供的网络架构的示意图。该网络架构可以包括：终端设备10、接入网设备20和核心网网元30。
终端设备10可以指UE(User Equipment，用户设备)、接入终端、用户单元、用户站、移动站、移动台、远方站、远程终端、移动设备、无线通信设备、用户代理或用户装置。在一些实施例中，终端设备10还可以是蜂窝电话、无绳电话、SIP电话、WLL(Wireless Local Loop，无线本地环路)站、PDA(Personal Digita1Assistant，个人数字处理)、具有无线通信功能的手持设备、计算设备或连接到无线调制解调器的其它处理设备、车载设备、可穿戴设备，5GS中的终端设备或者未来演进的PLMN(Pub1ic Land Mobi1e Network，公用陆地移动通信网络)中的终端设备等，本申请实施例对此并不限定。为方便描述，上面提到的设备统称为终端设备。终端设备10的数量通常为多个，每一个接入网设备20所管理的小区内可以分布一个或多个终端设备10。在本申请实施例中，“终端设备”和“UE”通常混用，但本领域技术人员可以理解其含义。
接入网设备20是一种部署在接入网中用以为终端设备10提供无线通信功能的设备。接入网设备20可以包括各种形式的宏基站，微基站，中继站，接入点等等。在采用不同的无线接入技术的系统中，具备接入网设备功能的设备的名称可能会有所不同，例如在5G NR系统中，称为gNodeB或者gNB。随着通信技术的演进，“接入网设备”这一名称可能会变化。为方便描述，本申请实施例中，上述为终端设备10提供无线通信功能的装置统称为接入网设备。在一些实施例中，通过接入网设备20，终端设备10和核心网网元30之间可以建立通信关系。示例性地，在LTE(Long Term Evolution，长期演进)系统中，接入网设备20可以是EUTRAN(Evolved Universal Terrestrial Radio Access Network，演进的通用陆地无线网)或者EUTRAN中的一个或者多个eNodeB；在5G NR系统中，接入网设备20可以是RAN(Radio Access Network，无线接入网)或者RAN中的一个或者多个gNB。
核心网网元30是部署在核心网中的网元，核心网网元30的功能主要是提供用户连接、对用户的管理以及对业务完成承载，作为承载网络提供到外部网络的接口。例如，5G NR系统中的核心网网元可以包括AMF(Access and Mobility Management Function，接入和移动性管理功能)、UPF(User Plane Function，用户平面功能)和SMF(Session Management Function，会话管理功能)等网元。另外，核心网网元可以看作是功能实体，一台物理设备上可以部署一个或者多个核心网网元。
在一些实施例中，接入网设备20与核心网网元30之间通过某种空口技术互相通信，例如5G NR系统中的NG接口。接入网设备20与终端设备10之间通过某种空口技术互相通信，例如Uu接口。
本申请实施例中的“5G NR系统”也可称为5G系统或者NR系统，但本领域技术人员可以理解其含义。本申请实施例描述的技术方案可以适用于LTE系统，也可以适用于5G NR系统，也可以适用于5G NR系统后续的演进系统，还可以适用于诸如NB-IoT(Narrow Band Internet of Things，窄带物联网)系统等其他通信系统，本申请对此不作限定。
在本申请实施例中，接入网设备可以为小区提供服务，终端设备通过该小区使用的载波上的传输资源(例如，频域资源，或者说，频谱资源)与接入网设备进行通信，该小区可以是接入网设备(例如基站)对应的小区，小区可以属于宏基站，也可以属于小小区(Small cell)对应的基站，这里的小小区可以包括：城市小区(Metro cell)、微小区(Micro cell)、微微小区(Pico cell)、毫微微小区(Femto cell)等，这些小小区具有覆盖范围小、发射功率低的特点，适用于提供高速率的数据传输服务。
请参考图2，其示出了本申请实施例提供的5GS(5th Generation System，第五代移动通信系统)的系统架构的示意图。如图2所示，该系统架构200可以包括：UE(也即上文介绍的“终端设备”)、(R)AN((Radio)Access Network，(无线)接入网)、Core(核心网)和DN(Data Network，数据网络)。其中，UE、(R)AN、Core是构成架构的主要成分，逻辑上它们可以分为用户面和控制面两部分，控制面负责移动网络的管理，用户面负责业务数据的传输。图中，NG2参考点位于(R)AN控制面和Core控制面之间，NG3参考点位于(R)AN用户面和Core用户面之间，NG6参考点位于Core用户面和数据网络之间。
UE：是移动用户与网络交互的入口，能够提供基本的计算能力、存储能力，向用户显示业务窗口，接收用户操作输入。UE会采用下一代空口技术，与(R)AN建立信号连接、数据连接，从而传输控制信号和业务数据到移动网络。
(R)AN：类似于传统网络里面的基站，部署在靠近UE的位置，为特定区域的授权用户提供入网功能，并能够根据用户的级别，业务的需求等使用不同质量的传输隧道传输用户数据。(R)AN能够管理自身的资源，合理利用，按需为UE提供接入服务，把控制信号和用户数据在UE和核心网之间转发。
Core：负责维护移动网络的签约数据，管理移动网络的网元，为UE提供会话管理、移动性管理、策 略管理、安全认证等功能。在UE注册的时候，为UE提供入网认证；在UE有业务请求时，为UE分配网络资源；在UE移动的时候，为UE更新网络资源；在UE空闲的时候，为UE提供快恢复机制：在UE去注册的时候，为UE释放网络资源；在UE有业务数据时，为UE提供数据路由功能，如转发上行数据到DN：或者从DN接收UE下行数据，转发到(R)AN，从而发送给UE。
DN：是为用户提供业务服务的数据网络，一般客户端位于UE，服务端位于数据网络。数据网络可以是私有网络，如局域网，也可以是不受运营商管控的外部网络，如Internet，还可以是运营商共同部署的专有网络，如为了配置IMS(IP Multimedia Subsystem，IP多媒体子系统)服务。
图3是在图2的基础上确定的详细架构，其中核心网用户面包括UPF；核心网控制面包括AUSF(Authentication Server Function，认证服务器功能网元)、AMF、SMF、NSSF(Network Slice Selection Function，网络切片选择功能网元)、NEF(Network Exposure Function，网络开放功能网元)、NRF(Network Repository Function，网络存储功能网元)、UDM(Unified Data Management，统一数据管理网元)、PCF(Policy Control Function，策略控制功能网元)、AF(Application Function，应用功能网元)。
在图3所示架构中，UE通过Uu口与(R)AN进行AS(Access Stratum，接入层)连接，交互AS消息及无线数据传输，UE通过N1口与AMF进行NAS(Non Access Stratum，非接入层)连接，交互NAS消息。AMF是核心网中的移动性管理功能，SMF是核心网中的会话管理功能，AMF在对UE进行移动性管理之外，还负责将会话管理相关消息在UE和SMF之间的转发。PCF是核心网中的策略管理功能，负责制定对UE的移动性管理、会话管理、计费等相关的策略。UPF是核心网中的用户面功能，通过N6接口与外部数据网络进行数据传输，通过N3接口与(R)AN进行数据传输。
需要说明的是，图2和图3中的各个网元之间的接口名称只是一个示例，具体实现中接口的名称可能为其他的名称，本申请实施例对此不作具体限定。图2和图3中包括的各个网元(比如SMF、AF、UPF等)的名称也仅是一个示例，对网元本身的功能不构成限定。在5GS以及未来其它的网络中，上述各个网元也可以是其他的名称，本申请实施例对此不作具体限定。例如，在6G网络中，上述各个网元中的部分或全部可以沿用5G中的术语，也可能采用其他名称，等等，在此进行统一说明，以下不再赘述。此外，应理解，上述各个网元之间的所传输的消息(或信令)的名称也仅仅是一个示例，对消息本身的功能不构成任何限定。
在介绍本申请技术方案之前，先对本申请涉及的一些背景技术知识进行介绍说明。以下相关技术作为可选方案与本申请实施例的技术方案可以进行任意结合，其均属于本申请实施例的保护范围。本申请实施例包括以下内容中的至少部分内容。
1.集中式联邦学习
随着终端设备(如移动终端)上的摄像头和传感器性能的不断提高，越来越多的终端设备可以收集对AI或ML模型训练必不可少的有价值的训练数据。对于许多AI或ML任务，终端设备收集的小样本数据对于训练全局模型具有重要的意义。
如图4所示的联邦学习，FL服务器通过聚合各个终端设备上报的局部训练结果来完成全局模型的训练。在每次训练迭代中，终端设备可以使用本地的训练数据，对从FL服务器下载的全局模型执行训练，然后通过上行信道向FL服务器上报中间训练结果(例如DNN(Deep Neural Network，深度神经网络)的梯度)。然后FL服务器对收集的梯度进行聚合，并更新全局模型。FL服务器通过下行信道将更新后的全局模型分发给参与联邦学习的终端设备，终端设备针对这一更新模型进行下一次的迭代训练。
2.加入Prose的联邦学习
当参与联邦学习的终端设备由于算力或电量问题，无法完成整个本地训练，而参与同一个联邦学习的其它终端设备也具备相同的模型，因此，可以将已经计算到某一步骤(例如某一层)的中间结果发送给其它终端设备，其它终端设备完成后续的计算。或者，当某个终端设备由于移动性的原因，在进行本地计算过程中，跑出了当前基站或FL服务器的覆盖范围，无法将训练后的结果传递给FL服务器，因此，可以借助Prose的方式，覆盖外的终端设备为远端终端设备(可称为Remote UE)，处于覆盖范围里的终端设备为中继终端设备(可称为Relay UE)，Remote UE借助Relay UE，将结果发送给FL服务器，从而保证联邦学习的顺利进行，其架构图如图5所示。
3.Prose架构
具有Prose能力的UE可以通过PC5接口与具有Prose能力的另外一个UE直接通信。
当一个UE既可以通过5G网络连接外部数据网络，还具有Prose能力时，这个UE可以充当RelayUE，另外一个具有Prose能力的Remote UE可以通过PC5接口与RelayUE建立直接连接，然后RelayUE与5G网络建立PDU会话与外部网络交互，如图6所示。
4.UE-to-Network Relay中的QoS处理
在Remote UE和UPF之间，通过Relay的流量可以通过在PC5接口上的PC5QoS控制和基于Uu口的Uu QoS控制分别实现。如图7所示。Relay UE具备5QI(5G QoS Identifier，5G服务质量标识)和PQI(PC5 5G QoS Identifier，PC5接口上的5G服务质量标识)之间的映射机制。
当一个QoS flow是通过网络发起建立的，SMF基于PCC rule和本地配置生成QoS Flow级别的QoS参数(例如，5QI、GFBR(Guaranteed Flow Bit Rate，保证流比特率)、MFBR(Maximum Flow Bit Rate，最大流比特率))，并在PDU会话建立或修改流程中告诉给Relay UE。Relay UE基于QoS mapping机制来确定PC5QoS flow的QoS参数，例如PQI，PC5QoS flow的GFBR和MFBR设置为和QoS flow的值相等。
当一个PC5的QoS flow是通过Remote UE发起建立或者修改的，Remote UE将QoS info(如PQI、GFBR、MFBR)提供给Relay UE。Relay UE将QoS info翻译成端到端的QoS需求。如果QoS mapping机制可以支持端到端的QoS需求，则Relay UE确定5QI进行Uu的QoS控制，确定PQI进行PC5的QoS控制。例如对于PDB(Packet Delay Budget，数据包时延预算)需求，端到端时延需求为100ms，则PQI可以为20ms，5QI为80ms。如果QoS mapping无法满足端到端的QoS需求，则Relay UE基于实现确定5QI进行Uu的QoS控制，确定PQI进行PC5的QoS控制。Relay UE将确定的PQI以及GFBR和MFBR放在接受消息中发送给Remote UE。Relay UE确定的PQI可以和Remote UE发送给relay UE的不同。
Relay UE后续可以执行PDU会话修改流程，请求网络侧授权Relay UE确定的5QI。
5.基于L3relay(层3中继)的5G Prose通信
如图8所示，基于L3relay的通信连接建立流程可以包括如下几个步骤：
S1、Relay UE(中继终端设备)可能在与Remote UE(远端终端设备)的连接建立之前先建立一个PDU会话来中继以后的数据。
S2、Remote UE执行发现流程来发现符合Remote UE需求的Relay UE。在此过程中，Remote UE得知Relay UE可以提供的连接业务。
S3、Remote UE选择一个Relay UE，并和Relay UE建立连接，如果没有符合要求的已经建立的PDU会话，在完成PC5连接建立之前，Relay UE向网络发起一个新的PDU会话建立流程。网络侧确定这个会话建立是针对于relay的数据传输，则发起QoS flow的建立和QoS参数的确定。Remote UE也可以在本步骤中，通过向Relay UE提供PC5QoS参数来发起QoS flow的建立，如前文QoS处理章节所述。
S4、对于IP类型的PDU会话和PC5接口上的IP流量，相应的IP地址被分配到Remote UE上。
S5、Remote UE可能在Layer-2(层2，简称L2)链路修改流程中向Relay UE提供PC5的QoS info，Relay UE基于PC5的QoS info确定新的QoS参数，并发起PDU会话修改流程，如QoS处理章节所述。
S6、Relay UE向SMF发送Remote UE报告，包括Remote User ID(远端终端设备的ID)、Remote UE info(远端终端设备的信息)。Remote User ID标识在步骤S3成功建立连接的UE，Remote UE info为辅助标识，用来标识其通过relay建立的PDU会话类型。如对于IP类型的PDU会话，为Remote UE IP info。
服务器对于执行AI操作的时间有着较为严格的要求，例如在执行联邦学习中，对于每一轮的完成时延有着严格的需求，才能保证模型训练的顺利进行和较快的收敛。服务器在选择一个UE作为AI操作的执行节点时，可以将该时延需求发送给UE，此时延需求包括了UE进行本地AI操作的处理时延和需要将生成的结果发送给服务器的传输时延。当一个UE出现如上文所述的一些情况下，需要将处理到某一步的中间数据发送给Relay UE，让其帮着完成后续的训练，并将训练结果发送给服务器时，Relay UE并不知道该AI操作需要的时间需求。因此，也无法根据现有的机制，来进行PC5和Uu口的QoS控制，从而无法保证Remote UE在采用Relay UE的方式下，仍然可以保证将AI操作结果按时发送到服务器。
基于此，本申请提供了一种无线通信方法，通过远端终端设备向中继终端设备发送第一信息，中继终端设备根据该第一信息确定目标AI操作的执行结果从远端终端设备到服务器的端到端传输时延，该目标AI操作是这两个终端设备合作完成的AI操作，使得中继终端设备能够根据该端到端传输时延进行准确的QoS控制，在基于中继方式合作完成AI操作的场景下，仍然可以保证将AI操作结果按时发送到服务器，提升可靠性。
在对本申请实施例进行介绍说明之前，先定义如下几种时延类型。
时延1：完成一个AI操作并将结果发送给服务器需要的时延，包括UE本地的处理时延，和将结果发送给服务器的传输时延，此时延为时延1，代表服务器对于一个AI操作的配置需求。
时延2：Remote UE在与Relay UE完成连接建立前，已经执行的本地处理时延。
时延3：时延1减时延2(时延3＝时延1-时延2)，即剩余的时延预算。
时延4：Relay UE在收到Remote UE发送的中间结果后，还需要进行处理才能完成AI本地操作所需的本地处理时延。
时延5：完成一个AI操作需要的本地处理时延，时延5＝时延2+时延4。
另外，定义如下参数。
参数1：Remote UE在时延2，已经进行的AI处理阶段。例如，已经本地训练到神经网络的某个层，或者已经本地训练的轮数。
参数2：Remote UE想要发送的中间数据的数据量大小。
请参考图9，其示出了本申请一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(910～930)中的至少一个步骤：
步骤910，远端终端设备向中继终端设备发送第一信息，远端终端设备和中继终端设备合作完成目标AI操作。
相应地，中继终端设备接收来自远端终端设备的第一信息。
在一些实施例中，第一信息用于确定目标AI操作的执行结果所对应的端到端传输时延，以进行QoS控制，端到端传输时延是指从远端终端设备到服务器的传输时延。服务器可以是发起执行目标AI操作的设备，例如该服务器可以是AI服务器或者其他任意的应用服务器或业务服务器，用于收集目标AI操作的执行结果。另外，目标AI操作可以是模型训练操作，例如训练神经网络模型。
步骤920，中继终端设备根据第一信息，确定目标AI操作的执行结果所对应的端到端传输时延，端到端传输时延是指从远端终端设备到服务器的传输时延。
在一些实施例中，端到端传输时延由中继终端设备根据远端终端设备提供的信息进一步计算确定。第一信息中包括用于确定端到端传输时延所需的信息。例如，第一信息包括：执行进度信息和第一时延信息，执行进度信息用于指示远端终端设备针对目标AI操作的执行进度，第一时延信息用于指示完成目标AI操作的剩余时延预算。中继终端设备可以根据执行进度信息和第一时延信息，确定端到端传输时延。
在一些实施例中，端到端传输时延由远端终端设备确定，并直接将该端到端传输时延指示给中继终端设备。第一信息中包括端到端传输时延，中继终端设备可以直接从第一信息中读取端到端传输时延。
有关第一信息以及中继终端设备根据该第一信息确定端到端传输时延方式的介绍说明，请参见下文实施例。
步骤930，中继终端设备根据端到端传输时延进行QoS控制。
在一些实施例中，中继终端设备可以根据端到端传输时延，对第一通信链路和/或第二通信链路进行QoS控制；其中，第一通信链路是指远端终端设备和中继终端设备之间的通信链路，第二通信链路是指中继终端设备和接入网设备之间的通信链路。例如，确定第一通信链路对应的QoS参数，和/或，确定第二通信链路对应的QoS参数。
在一些实施例中，中继终端设备根据端到端传输时延、远端终端设备和中继终端设备之间的第一通信链路对应的传输数据量、中继终端设备和接入网设备之间的第二通信链路对应的传输数据量，确定第一QoS参数和第二QoS参数；其中，第一QoS参数是指第一通信链路对应的QoS参数，第二QoS参数是指第二通信链路对应的QoS参数。
在一些实施例中，第一QoS参数包括但不限于以下至少之一：PQI、第一GFBR、第一MFBR。
在一些实施例中，第二QoS参数包括但不限于以下至少之一：5QI、第二GFBR、第二MFBR。
其中，第一QoS参数可以理解为PC5接口所对应的QoS参数，包括PQI、GFBR、MFBR等。第二QoS参数可以理解为Uu接口所对应的QoS参数，包括PQI、GFBR、MFBR等。为了区分PC5接口和Uu接口分别对应的GFBR，本申请中用第一GFBR和第二GFBR进行区分；同样地，为了区分PC5接口和Uu接口分别对应的MFBR，本申请中用第一MFBR和第二MFBR进行区分。中继终端设备所确定的上述第一GFBR和第二GFBR，可以相同，也可以不同。中继终端设备所确定的上述第一MFBR和第二MFBR，可以相同，也可以不同。例如，中继终端设备可以分别根据PC5接口上的传输数据量和Uu接口上的传输数据量，确定相应的QoS参数，实现QoS的精确和灵活控制。
此外，GFBR和MFBR是QoS流级别的码率控制参数，用于GBR类型的QoS流的码率控制。GFBR指示接入网设备(如基站)在平均时间窗内保证预留足够的资源为一个QoS流传输的码率。MFBR限制为QoS流传输的最大码率，超过MFBR的数据可能会被丢弃。在GFBR和MFBR之间传输的数据，接入网设备会根据QoS流的5QI所对应的调度优先级进行调度。
通过上述方式，中继终端设备根据端到端传输时延、PC5和Uu端口上分别的传输数据量，可以更为准确地确定出PC5和Uu端口上的QoS参数，从而建立合适的QoS流将目标AI操作的相关数据传输给服务器，保证该目标AI操作的顺利完成。
本申请实施例提供的技术方案，通过远端终端设备向中继终端设备发送第一信息，中继终端设备根据该第一信息确定目标AI操作的执行结果从远端终端设备到服务器的端到端传输时延，该目标AI操作是这 两个终端设备合作完成的AI操作，使得中继终端设备能够根据该端到端传输时延进行准确的QoS控制，在基于中继方式合作完成AI操作的场景下，仍然可以保证将AI操作结果按时发送到服务器，提升可靠性。而且，由于能够保证将AI操作结果按时发送到服务器，进而能够保证整个AI学习(如联邦学习)顺利进行，提升AI学习的性能和速率。
请参考图10，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(1010～1040)中的至少一个步骤：
步骤1010，远端终端设备向中继终端设备发送第一信息，第一信息包括：执行进度信息和第一时延信息，执行进度信息用于指示远端终端设备针对目标AI操作的执行进度，第一时延信息用于指示完成目标AI操作的剩余时延预算，远端终端设备和中继终端设备合作完成目标AI操作。
在一些实施例中，执行进度信息包括第一参数，该第一参数用于指示远端终端设备针对目标AI操作的已执行阶段。示例性地，该第一参数可以是上文所定义的参数1。
在一些实施例中，执行进度信息包括第二参数，该第二参数用于指示远端终端设备需要向中继终端设备发送的目标AI操作相关的中间数据的数据量。示例性地，该第二参数可以是上文所定义的参数2。
在一些实施例中，第一时延信息包括：完成目标AI操作的剩余时延预算。示例性地，该第一时延信息包括上文所定义的时延3。这样，中继终端设备可以直接从该第一时延信息中读取剩余时延预算。
在一些实施例中，第一时延信息包括：完成目标AI操作的剩余时延预算对应的PQI。示例性地，该第一时延信息包括上文所定义的时延3对应的PQI。这样，中继终端设备可以从该第一时延信息中读取剩余时延预算对应的PQI，然后根据该PQI确定剩余时延预算，如根据该PQI推导或预估得到剩余时延预算。
步骤1020，中继终端设备根据上述执行进度确定第二时延信息，第二时延信息用于指示中继终端设备完成目标AI操作的剩余阶段所需的处理时延。
在一些实施例中，中继终端设备可以根据执行进度信息确定远端终端设备针对目标AI操作的执行进度，然后根据该执行进度和该中继终端设备的本地配置，确定中继终端设备完成目标AI操作的剩余阶段所需的处理时延。示例性地，该第二时延信息包括上文所定义的时延4。
例如，目标AI操作包括对目标神经网络执行10轮训练，假设远端终端设备已经对该目标神经网络执行了6轮训练，远端终端设备通过向中继终端设备发送执行进度信息指示该远端终端设备已经对该目标神经网络执行了6轮训练，中继终端设备据此确定还需对该目标神经网络执行4轮训练，中继终端设备根据自身的本地配置(如自身的能力信息，包括但不限于算力等)预估执行上述4轮训练所需的时长，该时长即为第二时延信息(或者说时延4)。
步骤1030，中继终端设备根据第一时延信息和第二时延信息，确定端到端传输时延，端到端传输时延是指从远端终端设备到服务器的传输时延。
在一些实施例中，中继终端设备将完成目标AI操作的剩余时延预算，减去中继终端设备完成目标AI操作的剩余阶段所需的处理时延，得到端到端传输时延。也即，时延3减时延4等于端到端传输时延，用公式表示为：时延3-时延4＝端到端传输时延。
步骤1040，中继终端设备根据端到端传输时延进行QoS控制。
有关步骤1040的介绍说明可参见前后文其他实施例，本实施例对此不作赘述。
在本实施例中，提供了一种确定端到端传输时延的方式，由远端终端设备将自身针对目标AI操作的执行进度以及完成目标AI操作的剩余时延预算提供给中继终端设备，中继终端设备据此预估出自身完成目标AI操作的剩余阶段所需的处理时延，进而确定出端到端传输时延，由于端到端传输时延充分考虑了两个终端设备各自的处理量和能力等信息，该确定出的端到端传输时延具有较高的准确性，进而有助于提升QoS控制的准确性。
请参考图11，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(1110～1140)中的至少一个步骤：
步骤1110，远端终端设备根据第四时延信息和第五时延信息，确定端到端传输时延；其中，第四时延信息用于指示完成目标AI操作并将目标AI操作的执行结果发送给服务器所需的总时延，第五时延信息用于指示完成目标AI操作所需的处理时延，端到端传输时延是指从远端终端设备到服务器的传输时延，远端终端设备和中继终端设备合作完成目标AI操作。
在一些实施例中，第四时延信息包括上文所定义的时延1，第五时延信息包括上文所定义的时延5。
在一些实施例中，远端终端设备将完成目标AI操作并将目标AI操作的执行结果发送给服务器所需的总时延，减去完成目标AI操作所需的处理时延，得到端到端传输时延。也即，时延1减时延5等于端到端传输时延，用公式表示为：时延1-时延5＝端到端传输时延。
在一些实施例中，第四时延信息和第五时延信息由服务器规定，并提供给远端终端设备。例如，服务器在确定目标AI操作之后，提前规定好完成目标AI操作并将目标AI操作的执行结果发送给服务器所需的总时延，以及完成目标AI操作所需的处理时延。
步骤1120，远端终端设备向中继终端设备发送第一信息，第一信息包括：第三时延信息，第三时延信息用于指示端到端传输时延。
在一些实施例中，远端终端设备在确定出端到端传输时延之后，将该端到端传输时延发送给中继终端设备。
在一些实施例中，第一信息还包括：执行进度信息和第二时延信息，执行进度信息用于指示远端终端设备针对目标AI操作的执行进度，第二时延信息用于指示中继终端设备完成目标AI操作的剩余阶段所需的处理时延。
在一些实施例中，执行进度信息包括第一参数，该第一参数用于指示远端终端设备针对目标AI操作的已执行阶段。示例性地，该第一参数可以是上文所定义的参数1。
在一些实施例中，执行进度信息包括第二参数，该第二参数用于指示远端终端设备需要向中继终端设备发送的目标AI操作相关的中间数据的数据量。示例性地，该第二参数可以是上文所定义的参数2。
在一些实施例中，第二时延信息包括上文所定义的时延4。例如，远端终端设备根据第五时延信息和第六时延信息，确定第二时延信息；其中，第六时延信息用于指示远端终端设备针对目标AI操作的已处理时延。示例性地，第五时延信息包括上文所定义的时延5，第六时延信息包括上文所定义的时延2，时延4等于时延5减时延2，用公式表示为：时延4＝时延5-时延2。
步骤1130，中继终端设备根据第三时延信息确定端到端传输时延。
中继终端设备可以根据接收到的第三时延信息，确定出端到端传输时延。
步骤1140，中继终端设备根据端到端传输时延进行QoS控制。
有关步骤1140的介绍说明可参见前后文其他实施例，本实施例对此不作赘述。
在一些实施例中，在第一信息还包括执行进度信息和第二时延信息的情况下，中继终端设备还可以执行如下步骤：中继终端设备根据远端终端设备针对目标AI操作的执行进度，确定目标AI操作的剩余阶段，根据第二时延信息，执行目标AI操作的剩余阶段。例如，中继终端设备根据第二时延信息可以确定出自身完成目标AI操作的剩余阶段所需的处理时延，然后结合确定出的目标AI操作的剩余阶段，这就知道了中继终端设备要在多长时间内完成目标AI操作的剩余阶段，从而使用合适的算力等配置，执行该目标AI操作的剩余阶段，确保该目标AI操作的剩余阶段能够在上述第二时延信息所指示的时延要求内完成。
在本实施例中，提供了另一种确定端到端传输时延的方式，由远端终端设备根据提前配置、定义或规定好的总时延和完成目标AI操作所需的处理时延，确定出端到端传输时延，该确定出的端到端传输时延满足上述配置、定义或规定，进而有助于提升QoS控制的准确性。
在一些实施例中，远端终端设备通过连接建立请求向中继终端设备发送第一信息。远端终端设备向中继终端设备发送连接建立请求，该连接建立请求用于请求建立远端终端设备和中继终端设备之间的第一通信链路，该连接建立请求中包括第一信息。相应地，中继终端设备接收来自远端终端设备的连接建立请求。在一些实施例中，中继终端设备在接收到上述连接建立请求之后，可以建立远端终端设备和中继终端设备之间的第一通信链路，然后向远端终端设备发送连接建立响应，该连接建立响应用于指示中继终端设备同意建立第一通信链路。在一些实施例中，连接建立响应中包括第一通信链路对应的QoS参数。例如，中继终端设备根据连接建立请求中包含的第一信息，确定上文实施例所述的端到端传输时延，然后根据该端到端传输时延确定第一通信链路对应的QoS参数，并将该第一通信链路对应的QoS参数携带在连接建立响应中发送给远端终端设备。
通过上述方式，在连接建立流程中交互第一信息和QoS参数，可以更快速度地完成QoS流的建立，确保远端终端设备及时将目标AI操作的相关数据传递给中继终端设备，从而顺利完成AI操作。
在一些实施例中，远端终端设备通过链路修改请求向中继终端设备发送第一信息。远端终端设备向中继终端设备发送链路修改请求，该链路修改请求用于请求修改远端终端设备和中继终端设备之间已经建立的第一通信链路，该链路修改请求中包括第一信息。相应地，中继终端设备接收来自远端终端设备的链路修改请求。在一些实施例中，中继终端设备在接收到上述链路修改请求之后，可以确认是否同意修改第一通信链路，然后向远端终端设备发送链路修改响应，该链路修改响应用于指示中继终端设备同意修改第一通信链路。在一些实施例中，链路修改响应中包括第一通信链路对应的QoS参数。例如，中继终端设备根据链路修改请求中包含的第一信息，确定上文实施例所述的端到端传输时延，然后根据该端到端传输时延确定第一通信链路对应的QoS参数，并将该第一通信链路对应的QoS参数携带在链路修改响应中发送给 远端终端设备。
通过上述方式，提供了一种在链路修改流程中交互第一信息和QoS参数的方法，即触发PC5上的L2链路修改流程来完成满足要求的QoS流的建立，这种方式相比于在连接建立流程中完成QoS流的建立，及时性会相对较差一些，但提供了另外一种可选择的方式。
另外，这两种方式可以单独使用，也可以结合使用，例如在还未建立PC5连接或在即时性需求较高的情况下，通过在连接建立流程中交互第一信息和QoS参数，以便更快速度地完成QoS流的建立；在已经建立PC5连接或在即时性需求不高的情况下，通过在链路修改流程中交互第一信息和QoS参数，来完成满足要求的QoS流的建立。
在一些实施例中，中继终端设备还可以向核心网网元发送该中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。例如，中继终端设备根据端到端传输时延，并结合远端终端设备和中继终端设备之间的第一通信链路对应的传输数据量、中继终端设备和接入网设备之间的第二通信链路对应的传输数据量，确定该中继终端设备和接入网设备之间的第二通信链路对应的QoS参数，然后将该QoS参数发送给核心网网元。
在一些实施例中，第二通信链路对应的QoS参数通过PDU会话修改流程发送。例如，中继终端设备向核心网网元发送PDU会话修改请求，该PDU会话修改请求中包括第二通信链路对应的QoS参数。
通过上述方式，将第二通信链路对应的QoS参数发送给核心网网元，使得中继终端设备和核心网网元之间能够建立满足要求的QoS流，确保中继终端设备及时将目标AI操作的相关数据传递给核心网网元，并利用核心网网元发送给服务器，顺利完成AI操作。
请参考图12，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(A1～A8)中的至少一个步骤：
A1、Relay UE可能在与Remote UE的连接建立之前先建立一个PDU会话来中继以后的数据。
A2、Remote UE执行发现流程来发现符合Remote UE需求的Relay UE。在此过程中，Remote UE得知Relay UE可以提供的连接业务。
A3、Remote UE选择一个Relay UE，发送通信连接建立请求，请求中包括时延3、参数1或2，Remote UE可以将时延3作为一个单独的参数发送给Relay UE，也可以通过发送一个满足要求的PQI。例如，将时延3映射为一个PDB与其相等或相近的PQI，这样就不需要引入新的参数(即时延3)。
A4、Relay UE根据参数1或2和本地配置，预估出时延4，根据时延3或PQI中对应的PDB，得出AI操作结果需要的端到端传输时延，即从Remote UE到最后的服务器需要的传输时延。
此外，因为Relay UE需要对Remote UE发送的数据进行进一步的处理，因此，Relay UE不能按照现有机制将PC5和Uu接口对应的QoS参数中的GFBR和MFBR设置为相同。Relay UE基于参数1或2，以及根据自己执行完AI操作产生结果的数据大小，知道PC5和Uu上需要传输的数据大小，并根据端到端传输时延和各接口上需要传输的数据量大小，来确定PC5和Uu接口的QoS参数，包括PC5接口上的PQI、GFBR和MFBR，以及Uu接口上的5QI、GFBR和MFBR。PC5接口和Uu接口上的GFBR和MFBR可以不同。
A5、Relay UE在通信接受消息中将确定好的PC5接口上的QoS参数发送给Remote UE，包括PQI、GFBR和MFBR。
A6、对于IP类型的PDU会话和PC5接口上的IP流量，相应的IP地址被分配到Remote UE上。
需要说明的是，在此步骤之后，Remote UE和Relay UE之间的链路建立已经完成，Remote UE可以将中间数据发送给Relay UE。因此，通过本实施例的方法，通过在连接建立流程中发送时延3和参数1或2，可以在UE即将没电，或者即将移动到覆盖范围外时，最快速度将中间数据发送给Relay UE。
A7、Relay UE根据步骤A4确定的Uu接口上的QoS参数发起PDU会话修改流程，建立符合条件的Uu接口上的QoS flow。
A8、Relay UE向SMF发送Remote UE报告，包括Remote User ID和Remote UE info。Remote User ID标识在步骤A3成功建立连接的UE，Remote UE info为辅助标识，用来标识其通过relay建立的PDU会话类型。如对于IP类型的PDU会话，为Remote UE IP info。
在本实施例中，应用层将时延1配置给Remote UE，Remote UE执行到某个AI操作阶段，可以得到参数1、参数2和时延2，基于时延1，计算出时延3。Remote UE将时延3、参数1或参数2发送给Relay UE。Relay UE根据参数1或参数2和本地配置(如本地的一些能力，如处理器核数等算力)，预估出时延4，根据时延3-时延4，得出AI操作结果需要的端到端传输时延，即从Remote UE到最后的服务器需要的传输时延。
请参考图13，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(B1～B8)中的至少一个步骤：
B1、Relay UE可能在与Remote UE的连接建立之前先建立一个PDU会话来中继以后的数据。
B2、Remote UE执行发现流程来发现符合Remote UE需求的Relay UE。在此过程中，Remote UE得知Relay UE可以提供的连接业务。
B3、Remote UE选择一个Relay UE，并和Relay UE建立连接，如果没有符合要求的已经建立的PDU会话，在完成PC5连接建立之前，Relay UE向网络发起一个新的PDU会话建立流程。网络侧确定这个会话建立是针对于relay的数据传输，则发起QoS flow的建立和QoS参数的确定。Remote UE也可以在本步骤中，通过向Relay UE提供PC5QoS参数来发起QoS flow的建立，如前文QoS处理章节所述。
B4、对于IP类型的PDU会话和PC5接口上的IP流量，相应的IP地址被分配到Remote UE上。
B5、Remote UE发送链路修改请求，请求中包括时延3，还包括参数1或2。Remote UE可以将时延3作为一个单独的参数发送给Relay UE，也可以通过发送一个满足要求的PQI，例如，将时延3映射为一个PDB与其相等或相近的PQI。
B6、Relay UE根据参数1或2和本地配置，预估出时延4，根据时延3或PQI中对应的PDB，得出AI操作结果需要的端到端传输时延，即从Remote UE到最后的服务器需要的传输时延。
此外，因为Relay UE需要对Remote UE发送的数据进行进一步的处理，因此，Relay UE不能按照现有机制将PC5和Uu接口对应的QoS参数中的GFBR和MFBR设置为相同。Relay UE基于参数1或2，以及根据自己执行完AI操作产生结果的数据大小，知道PC5和Uu上需要传输的数据大小，并根据端到端传输时延和各接口上需要传输的数据量大小，来确定PC5和Uu接口的QoS参数，包括PC5接口上的PQI、GFBR和MFBR，以及Uu接口上的5QI、GFBR和MFBR。PC5接口和Uu接口上的GFBR和MFBR可以不同。
此外，Relay UE发起PDU会话修改请求，携带Relay UE确定的Uu口的QoS参数，来建立符合条件的Uu上的QoS flow。
B7、Relay UE发送链路修改接受消息，在消息中携带Relay UE确定的PC5QoS参数。
B8、Relay UE向SMF发送Remote UE报告，包括Remote User ID和Remote UE info。Remote User ID标识在步骤B3成功建立连接的UE，Remote UE info为辅助标识，用来标识其通过relay建立的PDU会话类型。如对于IP类型的PDU会话，为Remote UE IP info。
在本实施例中，由于在链路修改流程中传递了相关参数，使得Relay UE可以准确确定出PC5和Uu上的QoS参数。因此，在步骤B7完成之后，Remote UE才能将中间数据发送给Relay UE。与图12所示实施例相比稍慢。
请参考图14，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(C1～C8)中的至少一个步骤：
C1、Relay UE可能在与Remote UE的连接建立之前先建立一个PDU会话来中继以后的数据。
C2、Remote UE执行发现流程来发现符合Remote UE需求的Relay UE。在此过程中，Remote UE得知Relay UE可以提供的连接业务。
C3、Remote UE选择一个Relay UE，发送通信连接建立请求，请求中包括端到端传输时延、时延4和参数2。
在本实施例中，AI服务器规定好时延1和时延5，即规定了本地处理时延，将这些参数配置给remote UE。Remote UE通过时延1-时延5，可以得到端到端传输时延。
C4、Relay UE从通信连接建立请求中读取端到端传输时延、时延4和参数2，并根据时延4和参数2进行AI操作，完成剩余阶段的处理。
另外，Relay UE按照上文图12和13实施例所述，基于端到端传输时延和分别需要在PC5和Uu接口上传输的数据量，确定PC5和Uu接口的QoS参数。
C5、Relay UE在通信接受消息中将确定好的PC5接口上的QoS参数发送给Remote UE，包括PQI、GFBR和MFBR。
C6、对于IP类型的PDU会话和PC5接口上的IP流量，相应的IP地址被分配到Remote UE上。
需要说明的是，在此步骤之后，Remote UE和Relay UE之间的链路建立已经完成，Remote UE可以将中间数据发送给Relay UE。因此，通过本实施例的方法，通过在连接建立流程中发送端到端传输时延、时延4和参数2，可以在UE即将没电，或者即将移动到覆盖范围外时，最快速度将中间数据发送给Relay UE。
C7、Relay UE根据步骤C4确定的Uu接口上的QoS参数发起PDU会话修改流程，建立符合条件的 Uu接口上的QoS flow。
C8、Relay UE向SMF发送Remote UE报告，包括Remote User ID和Remote UE info。Remote User ID标识在步骤C3成功建立连接的UE，Remote UE info为辅助标识，用来标识其通过relay建立的PDU会话类型。如对于IP类型的PDU会话，为Remote UE IP info。
请参考图15，其示出了本申请另一个实施例提供的无线通信方法的流程图。该方法可应用于图1或图6所示的网络架构中。该方法可以包括如下几个步骤(D1～D8)中的至少一个步骤：
D1、Relay UE可能在与Remote UE的连接建立之前先建立一个PDU会话来中继以后的数据。
D2、Remote UE执行发现流程来发现符合Remote UE需求的Relay UE。在此过程中，Remote UE得知Relay UE可以提供的连接业务。
D3、Remote UE选择一个Relay UE，并和Relay UE建立连接，如果没有符合要求的已经建立的PDU会话，在完成PC5连接建立之前，Relay UE向网络发起一个新的PDU会话建立流程。网络侧确定这个会话建立是针对于relay的数据传输，则发起QoS flow的建立和QoS参数的确定。Remote UE也可以在本步骤中，通过向Relay UE提供PC5QoS参数来发起QoS flow的建立，如前文QoS处理章节所述。
D4、对于IP类型的PDU会话和PC5接口上的IP流量，相应的IP地址被分配到Remote UE上。
D5、Remote UE发送链路修改请求，请求中包括端到端传输时延、时延4和参数2。
在本实施例中，AI服务器规定好时延1和时延5，即规定了本地处理时延，将这些参数配置给remote UE。Remote UE通过时延1-时延5，可以得到端到端传输时延。
D6、Relay UE从链路修改请求中读取端到端传输时延、时延4和参数2，并根据时延4和参数2进行AI操作，完成剩余阶段的处理。
另外，Relay UE按照上文图12和13实施例所述，基于端到端传输时延和分别需要在PC5和Uu接口上传输的数据量，确定PC5和Uu接口的QoS参数。
此外，Relay UE发起PDU会话修改请求，携带Relay UE确定的Uu口的QoS参数，来建立符合条件的Uu上的QoS flow。
D7、Relay UE发送链路修改接受消息，在消息中携带Relay UE确定的PC5QoS参数。
D8、Relay UE向SMF发送Remote UE报告，包括Remote User ID和Remote UE info。Remote User ID标识在步骤D3成功建立连接的UE，Remote UE info为辅助标识，用来标识其通过relay建立的PDU会话类型。如对于IP类型的PDU会话，为Remote UE IP info。
下述为本申请装置实施例，可以用于执行本申请方法实施例。对于本申请装置实施例中未披露的细节，请参照本申请方法实施例。
请参考图16，其示出了本申请一个实施例提供的无线通信装置的框图。该装置具有实现上述中继终端设备所执行的方法示例的功能，所述功能可以由硬件实现，也可以由硬件执行相应的软件实现。该装置可以是中继终端设备，也可以设置在中继终端设备中。如图16所示，该装置1600可以包括：接收模块1610、确定模块1620和控制模块1630。
接收模块1610，用于接收来自远端终端设备的第一信息，所述远端终端设备和中继终端设备合作完成目标AI操作。
确定模块1620，用于根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
控制模块1630，用于根据所述端到端传输时延进行QoS控制。
在一些实施例中，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算。所述确定模块1620，用于根据所述执行进度确定第二时延信息，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延；根据所述第一时延信息和所述第二时延信息，确定所述端到端传输时延。
在一些实施例中，所述第一时延信息包括：所述剩余时延预算；或者，所述剩余时延预算对应的PQI。
在一些实施例中，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
在一些实施例中，所述端到端传输时延由所述远端终端设备根据第四时延信息和第五时延信息确定；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
在一些实施例中，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端 设备。
在一些实施例中，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。如图16所示，所述装置1600还包括：执行模块1640，用于根据所述执行进度，确定所述目标AI操作的剩余阶段；根据所述第二时延信息，执行所述目标AI操作的剩余阶段。
在一些实施例中，所述执行进度信息包括：第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；或者，第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
在一些实施例中，所述控制模块1630，用于根据所述端到端传输时延、所述远端终端设备和所述中继终端设备之间的第一通信链路对应的传输数据量、所述中继终端设备和接入网设备之间的第二通信链路对应的传输数据量，确定第一QoS参数和第二QoS参数；其中，所述第一QoS参数是指所述第一通信链路对应的QoS参数，所述第二QoS参数是指所述第二通信链路对应的QoS参数。
在一些实施例中，所述第一QoS参数包括以下至少之一：PQI、第一GFBR、第一MFBR。
在一些实施例中，所述第二QoS参数包括以下至少之一：5QI、第二GFBR、第二MFBR。
在一些实施例中，所述接收模块1610，用于接收来自所述远端终端设备的连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
在一些实施例中，如图16所示，所述装置1600还包括：发送模块1650，用于向所述远端终端设备发送连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
在一些实施例中，所述接收模块1610，用于接收来自所述远端终端设备的链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
在一些实施例中，如图16所示，所述装置1600还包括：发送模块1650，用于向所述远端终端设备发送链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
在一些实施例中，如图16所示，所述装置1600还包括：发送模块1650，用于向核心网网元发送所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
在一些实施例中，所述第二通信链路对应的QoS参数通过PDU会话修改流程发送。
请参考图17，其示出了本申请另一个实施例提供的无线通信装置的框图。该装置具有实现上述远端终端设备所执行的方法示例的功能，所述功能可以由硬件实现，也可以由硬件执行相应的软件实现。该装置可以是远端终端设备，也可以设置在远端终端设备中。如图17所示，该装置1700可以包括：发送模块1710。
发送模块1710，用于向中继终端设备发送第一信息，远端终端设备和所述中继终端设备合作完成目标AI操作。其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
在一些实施例中，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算。其中，所述端到端传输时延由所述中继终端设备根据所述第一时延信息和第二时延信息确定，所述第二时延信息根据所述执行进度确定，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
在一些实施例中，所述第一时延信息包括：所述剩余时延预算；或者，所述剩余时延预算对应的PQI。
在一些实施例中，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
在一些实施例中，如图17所示，所述装置1700还包括：确定模块1720，用于根据第四时延信息和第五时延信息，确定所述端到端传输时延；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
在一些实施例中，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端设备。
在一些实施例中，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示 所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
在一些实施例中，所述执行进度信息包括：第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；或者，第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
在一些实施例中，所述端到端传输时延用于确定第一QoS参数和第二QoS参数；其中，所述第一QoS参数是指所述远端终端设备和所述中继终端设备之间的第一通信链路对应的QoS参数，所述第二QoS参数是指所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
在一些实施例中，所述第一QoS参数包括以下至少之一：PQI、第一GFBR、第一MFBR。
在一些实施例中，所述第二QoS参数包括以下至少之一：5QI、第二GFBR、第二MFBR。
在一些实施例中，所述发送模块1710，用于向所述中继终端设备发送连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
在一些实施例中，如图17所示，所述装置1700还包括：接收模块1730，用于接收来自所述中继终端设备的连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
在一些实施例中，所述发送模块1710，用于向所述中继终端设备发送链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
在一些实施例中，如图17所示，所述装置1700还包括：接收模块1730，用于接收来自所述中继终端设备的链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
需要说明的一点是，上述实施例提供的装置在实现其功能时，仅以上述各个功能模块的划分进行举例说明，实际应用中，可以根据实际需要而将上述功能分配由不同的功能模块完成，即将设备的内容结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
请参考图18，其示出了本申请一个实施例提供的终端设备的结构示意图。该终端设备1800可以包括：处理器1801、收发器1802以及存储器1803。
处理器1801包括一个或者一个以上处理核心，处理器1801通过运行软件程序以及模块，从而执行各种功能应用以及信息处理。
收发器1802可以包括接收器和发射器，比如，该接收器和发射器可以实现为同一个无线通信组件，该无线通信组件可以包括一块无线通信芯片以及射频天线。
存储器1803可以与处理器1801以及收发器1802相连。
存储器1803可用于存储处理器执行的计算机程序，处理器1801用于执行该计算机程序，以实现上述方法实施例中的远端终端设备或者中继终端设备执行的各个步骤。
此外，存储器1803可以由任何类型的易失性或非易失性存储设备或者它们的组合实现，易失性或非易失性存储设备包括但不限于：磁盘或光盘，电可擦除可编程只读存储器，可擦除可编程只读存储器，静态随时存取存储器，只读存储器，磁存储器，快闪存储器，可编程只读存储器。
对于本实施例中未详细说明的细节，可参见上文实施例，此处不再一一赘述。
在一些实施例中，在终端设备1800为上文实施例介绍的中继终端设备的情况下，
所述收发器1802，用于接收来自远端终端设备的第一信息，所述远端终端设备和所述中继终端设备合作完成目标AI操作；
所述处理器1801，用于根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延；根据所述端到端传输时延进行服务质量QoS控制。
在一些实施例中，在终端设备1800为上文实施例介绍的远端终端设备的情况下，
所述收发器1802，用于向中继终端设备发送第一信息，所述远端终端设备和所述中继终端设备合作完成目标AI操作；其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
对于本实施例中未详细说明的细节，可参见上文实施例，此处不再一一赘述。
本申请实施例还提供了一种计算机可读存储介质，所述存储介质中存储有计算机程序，所述计算机程序用于被中继终端设备的处理器执行，以实现上述中继终端设备所执行的无线通信方法。
本申请实施例还提供了一种计算机可读存储介质，所述存储介质中存储有计算机程序，所述计算机程序用于被远端终端设备的处理器执行，以实现上述远端终端设备所执行的无线通信方法。
在一些实施例中，该计算机可读存储介质可以包括：ROM(Read-Only Memory，只读存储器)、RAM(Random-Access Memory，随机存储器)、SSD(Solid State Drives，固态硬盘)或光盘等。其中，随机存取记忆体可以包括ReRAM(Resistance Random Access Memory，电阻式随机存取记忆体)和DRAM(Dynamic Random Access Memory，动态随机存取存储器)。
本申请实施例还提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片在中继终端设备上运行时，用于实现上述中继终端设备所执行的无线通信方法。
本申请实施例还提供了一种芯片，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片在远端终端设备上运行时，用于实现上述远端终端设备所执行的无线通信方法。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括计算机指令，所述计算机指令存储在计算机可读存储介质中，中继终端设备的处理器从所述计算机可读存储介质读取并执行所述计算机指令，以实现上述中继终端设备所执行的无线通信方法。
本申请实施例还提供了一种计算机程序产品，所述计算机程序产品包括计算机指令，所述计算机指令存储在计算机可读存储介质中，远端终端设备的处理器从所述计算机可读存储介质读取并执行所述计算机指令，以实现上述远端终端设备所执行的无线通信方法。
应理解，在本申请的实施例中提到的“指示”可以是直接指示，也可以是间接指示，还可以是表示具有关联关系。举例说明，A指示B，可以表示A直接指示B，例如B可以通过A获取；也可以表示A间接指示B，例如A指示C，B可以通过C获取；还可以表示A和B之间具有关联关系。
在本申请实施例的描述中，术语“对应”可表示两者之间具有直接对应或间接对应的关系，也可以表示两者之间具有关联关系，也可以是指示与被指示、配置与被配置等关系。
在本申请一些实施例中，“预定义的”可以通过在设备(例如，包括终端设备和核心网网元)中预先保存相应的代码、表格或其他可用于指示相关信息的方式来实现，本申请对于其具体的实现方式不作限定。比如预定义的可以是指协议中定义的。
在本申请一些实施例中，所述“协议”可以指通信领域的标准协议，例如可以包括LTE协议、NR协议以及应用于未来的通信系统中的相关协议，本申请对此不作限定。
在本文中提及的“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这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。
另外，本文中描述的步骤编号，仅示例性示出了步骤间的一种可能的执行先后顺序，在一些其它实施例中，上述步骤也可以不按照编号顺序来执行，如两个不同编号的步骤同时执行，或者两个不同编号的步骤按照与图示相反的顺序执行，本申请实施例对此不作限定。
本领域技术人员应该可以意识到，在上述一个或多个示例中，本申请实施例所描述的功能可以用硬件、软件、固件或它们的任意组合来实现。当使用软件实现时，可以将这些功能存储在计算机可读介质中或者作为计算机可读介质上的一个或多个指令或代码进行传输。计算机可读介质包括计算机存储介质和通信介质，其中通信介质包括便于从一个地方向另一个地方传送计算机程序的任何介质。存储介质可以是通用或专用计算机能够存取的任何可用介质。
以上所述仅为本申请的示例性实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (68)

  1. 一种无线通信方法，其特征在于，所述方法由中继终端设备执行，所述方法包括：
    接收来自远端终端设备的第一信息，所述远端终端设备和所述中继终端设备合作完成目标人工智能AI操作；
    根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延；
    根据所述端到端传输时延进行服务质量QoS控制。
  2. 根据权利要求1所述的方法，其特征在于，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算；
    所述根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，包括：
    根据所述执行进度确定第二时延信息，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延；
    根据所述第一时延信息和所述第二时延信息，确定所述端到端传输时延。
  3. 根据权利要求2所述的方法，其特征在于，所述第一时延信息包括：
    所述剩余时延预算；
    或者，
    所述剩余时延预算对应的PC5接口上的5G服务质量标识PQI。
  4. 根据权利要求1所述的方法，其特征在于，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
  5. 根据权利要求4所述的方法，其特征在于，所述端到端传输时延由所述远端终端设备根据第四时延信息和第五时延信息确定；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
  6. 根据权利要求5所述的方法，其特征在于，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端设备。
  7. 根据权利要求4至6任一项所述的方法，其特征在于，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延；
    所述方法还包括：
    根据所述执行进度，确定所述目标AI操作的剩余阶段；
    根据所述第二时延信息，执行所述目标AI操作的剩余阶段。
  8. 根据权利要求2或7所述的方法，其特征在于，所述执行进度信息包括：
    第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；
    或者，
    第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
  9. 根据权利要求1至8任一项所述的方法，其特征在于，所述根据所述端到端传输时延进行QoS控制，包括：
    根据所述端到端传输时延、所述远端终端设备和所述中继终端设备之间的第一通信链路对应的传输数据量、所述中继终端设备和接入网设备之间的第二通信链路对应的传输数据量，确定第一QoS参数和第二QoS参数；
    其中，所述第一QoS参数是指所述第一通信链路对应的QoS参数，所述第二QoS参数是指所述第二通信链路对应的QoS参数。
  10. 根据权利要求9所述的方法，其特征在于，所述第一QoS参数包括以下至少之一：PQI、第一保证流比特率GFBR、第一最大流比特率MFBR。
  11. 根据权利要求9或10所述的方法，其特征在于，所述第二QoS参数包括以下至少之一：5G服务质量标识5QI、第二保证流比特率GFBR、第二最大流比特率MFBR。
  12. 根据权利要求1至11任一项所述的方法，其特征在于，所述接收来自远端终端设备的第一信息，包括：
    接收来自所述远端终端设备的连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
  13. 根据权利要求12所述的方法，其特征在于，所述方法还包括：
    向所述远端终端设备发送连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
  14. 根据权利要求1至11任一项所述的方法，其特征在于，所述接收来自远端终端设备的第一信息，包括：
    接收来自所述远端终端设备的链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
  15. 根据权利要求14所述的方法，其特征在于，所述方法还包括：
    向所述远端终端设备发送链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
  16. 根据权利要求1至15任一项所述的方法，其特征在于，所述方法还包括：
    向核心网网元发送所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
  17. 根据权利要求16所述的方法，其特征在于，所述第二通信链路对应的QoS参数通过协议数据单元PDU会话修改流程发送。
  18. 一种无线通信方法，其特征在于，所述方法由远端终端设备执行，所述方法包括：
    向中继终端设备发送第一信息，所述远端终端设备和所述中继终端设备合作完成目标人工智能AI操作；
    其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行服务质量QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
  19. 根据权利要求18所述的方法，其特征在于，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算；
    其中，所述端到端传输时延由所述中继终端设备根据所述第一时延信息和第二时延信息确定，所述第二时延信息根据所述执行进度确定，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
  20. 根据权利要求19所述的方法，其特征在于，所述第一时延信息包括：
    所述剩余时延预算；
    或者，
    所述剩余时延预算对应的PC5接口上的5G服务质量标识PQI。
  21. 根据权利要求18所述的方法，其特征在于，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
  22. 根据权利要求21所述的方法，其特征在于，所述方法还包括：
    根据第四时延信息和第五时延信息，确定所述端到端传输时延；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
  23. 根据权利要求22所述的方法，其特征在于，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端设备。
  24. 根据权利要求21至23任一项所述的方法，其特征在于，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
  25. 根据权利要求19或24所述的方法，其特征在于，所述执行进度信息包括：
    第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；
    或者，
    第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
  26. 根据权利要求18至25任一项所述的方法，其特征在于，所述端到端传输时延用于确定第一QoS参数和第二QoS参数；
    其中，所述第一QoS参数是指所述远端终端设备和所述中继终端设备之间的第一通信链路对应的QoS参数，所述第二QoS参数是指所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
  27. 根据权利要求26所述的方法，其特征在于，所述第一QoS参数包括以下至少之一：PQI、第一保证流比特率GFBR、第一最大流比特率MFBR。
  28. 根据权利要求26或27所述的方法，其特征在于，所述第二QoS参数包括以下至少之一：5G服务质量标识5QI、第二保证流比特率GFBR、第二最大流比特率MFBR。
  29. 根据权利要求18至28任一项所述的方法，其特征在于，所述向中继终端设备发送第一信息，包括：
    向所述中继终端设备发送连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
  30. 根据权利要求29所述的方法，其特征在于，所述方法还包括：
    接收来自所述中继终端设备的连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
  31. 根据权利要求18至28任一项所述的方法，其特征在于，所述向中继终端设备发送第一信息，包括：
    向所述中继终端设备发送链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
  32. 根据权利要求31所述的方法，其特征在于，所述方法还包括：
    接收来自所述中继终端设备的链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
  33. 一种无线通信装置，其特征在于，所述装置包括：
    接收模块，用于接收来自远端终端设备的第一信息，所述远端终端设备和中继终端设备合作完成目标人工智能AI操作；
    确定模块，用于根据所述第一信息，确定所述目标AI操作的执行结果所对应的端到端传输时延，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延；
    控制模块，用于根据所述端到端传输时延进行服务质量QoS控制。
  34. 根据权利要求33所述的装置，其特征在于，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算；
    所述确定模块，用于根据所述执行进度确定第二时延信息，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延；根据所述第一时延信息和所述第二时延信息，确定所述端到端传输时延。
  35. 根据权利要求34所述的装置，其特征在于，所述第一时延信息包括：
    所述剩余时延预算；
    或者，
    所述剩余时延预算对应的PC5接口上的5G服务质量标识PQI。
  36. 根据权利要求33所述的装置，其特征在于，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
  37. 根据权利要求36所述的装置，其特征在于，所述端到端传输时延由所述远端终端设备根据第四时延信息和第五时延信息确定；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
  38. 根据权利要求37所述的装置，其特征在于，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端设备。
  39. 根据权利要求36至38任一项所述的装置，其特征在于，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延；
    所述装置还包括：
    执行模块，用于根据所述执行进度，确定所述目标AI操作的剩余阶段；根据所述第二时延信息，执行所述目标AI操作的剩余阶段。
  40. 根据权利要求34或39所述的装置，其特征在于，所述执行进度信息包括：
    第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；
    或者，
    第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
  41. 根据权利要求33至40任一项所述的装置，其特征在于，
    所述控制模块，用于根据所述端到端传输时延、所述远端终端设备和所述中继终端设备之间的第一通信链路对应的传输数据量、所述中继终端设备和接入网设备之间的第二通信链路对应的传输数据量，确定第一QoS参数和第二QoS参数；
    其中，所述第一QoS参数是指所述第一通信链路对应的QoS参数，所述第二QoS参数是指所述第二通信链路对应的QoS参数。
  42. 根据权利要求41所述的装置，其特征在于，所述第一QoS参数包括以下至少之一：PQI、第一保证流比特率GFBR、第一最大流比特率MFBR。
  43. 根据权利要求41或42所述的装置，其特征在于，所述第二QoS参数包括以下至少之一：5G服务质量标识5QI、第二保证流比特率GFBR、第二最大流比特率MFBR。
  44. 根据权利要求33至43任一项所述的装置，其特征在于，
    所述接收模块，用于接收来自所述远端终端设备的连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
  45. 根据权利要求44所述的装置，其特征在于，所述装置还包括：
    发送模块，用于向所述远端终端设备发送连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
  46. 根据权利要求33至43任一项所述的装置，其特征在于，
    所述接收模块，用于接收来自所述远端终端设备的链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
  47. 根据权利要求46所述的装置，其特征在于，所述装置还包括：
    发送模块，用于向所述远端终端设备发送链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
  48. 根据权利要求33至47任一项所述的装置，其特征在于，所述装置还包括：
    发送模块，用于向核心网网元发送所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
  49. 根据权利要求48所述的装置，其特征在于，所述第二通信链路对应的QoS参数通过协议数据单元PDU会话修改流程发送。
  50. 一种无线通信装置，其特征在于，所述装置包括：
    发送模块，用于向中继终端设备发送第一信息，远端终端设备和所述中继终端设备合作完成目标人工智能AI操作；
    其中，所述第一信息用于确定所述目标AI操作的执行结果所对应的端到端传输时延，以进行服务质量QoS控制，所述端到端传输时延是指从所述远端终端设备到服务器的传输时延。
  51. 根据权利要求50所述的装置，其特征在于，所述第一信息包括：执行进度信息和第一时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第一时延信息用于指示完成所述目标AI操作的剩余时延预算；
    其中，所述端到端传输时延由所述中继终端设备根据所述第一时延信息和第二时延信息确定，所述第二时延信息根据所述执行进度确定，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
  52. 根据权利要求51所述的装置，其特征在于，所述第一时延信息包括：
    所述剩余时延预算；
    或者，
    所述剩余时延预算对应的PC5接口上的5G服务质量标识PQI。
  53. 根据权利要求50所述的装置，其特征在于，所述第一信息包括：第三时延信息，所述第三时延信息用于指示所述端到端传输时延。
  54. 根据权利要求53所述的装置，其特征在于，所述装置还包括：
    确定模块，用于根据第四时延信息和第五时延信息，确定所述端到端传输时延；其中，所述第四时延信息用于指示完成所述目标AI操作并将所述目标AI操作的执行结果发送给所述服务器所需的总时延，所述第五时延信息用于指示完成所述目标AI操作所需的处理时延。
  55. 根据权利要求54所述的装置，其特征在于，所述第四时延信息和所述第五时延信息由所述服务器规定，并提供给所述远端终端设备。
  56. 根据权利要求53至55任一项所述的装置，其特征在于，所述第一信息还包括：执行进度信息和第二时延信息，所述执行进度信息用于指示所述远端终端设备针对所述目标AI操作的执行进度，所述第二时延信息用于指示所述中继终端设备完成所述目标AI操作的剩余阶段所需的处理时延。
  57. 根据权利要求51或56所述的装置，其特征在于，所述执行进度信息包括：
    第一参数，用于指示所述远端终端设备针对所述目标AI操作的已执行阶段；
    或者，
    第二参数，用于指示所述远端终端设备需要向所述中继终端设备发送的所述目标AI操作相关的中间数据的数据量。
  58. 根据权利要求50至57任一项所述的装置，其特征在于，所述端到端传输时延用于确定第一QoS参数和第二QoS参数；
    其中，所述第一QoS参数是指所述远端终端设备和所述中继终端设备之间的第一通信链路对应的QoS参数，所述第二QoS参数是指所述中继终端设备和接入网设备之间的第二通信链路对应的QoS参数。
  59. 根据权利要求58所述的装置，其特征在于，所述第一QoS参数包括以下至少之一：PQI、第一保证流比特率GFBR、第一最大流比特率MFBR。
  60. 根据权利要求58或59所述的装置，其特征在于，所述第二QoS参数包括以下至少之一：5G服务质量标识5QI、第二保证流比特率GFBR、第二最大流比特率MFBR。
  61. 根据权利要求50至60任一项所述的装置，其特征在于，
    所述发送模块，用于向所述中继终端设备发送连接建立请求，所述连接建立请求用于请求建立所述远端终端设备和所述中继终端设备之间的第一通信链路，所述连接建立请求中包括所述第一信息。
  62. 根据权利要求61所述的装置，其特征在于，所述装置还包括：
    接收模块，用于接收来自所述中继终端设备的连接建立响应，所述连接建立响应用于指示所述中继终端设备同意建立所述第一通信链路，所述连接建立响应中包括所述第一通信链路对应的QoS参数。
  63. 根据权利要求50至60任一项所述的装置，其特征在于，
    所述发送模块，用于向所述中继终端设备发送链路修改请求，所述链路修改请求用于请求修改所述远端终端设备和所述中继终端设备之间已经建立的第一通信链路，所述链路修改请求中包括所述第一信息。
  64. 根据权利要求63所述的装置，其特征在于，所述装置还包括：
    接收模块，用于接收来自所述中继终端设备的链路修改响应，所述链路修改响应用于指示所述中继终端设备同意修改所述第一通信链路，所述链路修改响应中包括所述第一通信链路对应的QoS参数。
  65. 一种终端设备，其特征在于，所述终端设备包括处理器和存储器，所述存储器中存储有计算机程序，所述处理器执行所述计算机程序以实现如权利要求1至17任一项所述的方法，或者实现如权利要求18至32任一项所述的方法。
  66. 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，所述计算机程序用于被处理器执行，以实现如权利要求1至17任一项所述的方法，或者实现如权利要求18至32任一项所述的方法。
  67. 一种芯片，其特征在于，所述芯片包括可编程逻辑电路和/或程序指令，当所述芯片运行时，用于实现如权利要求1至17任一项所述的方法，或者实现如权利要求18至32任一项所述的方法。
  68. 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计算机指令，所述计算机指令存储在计算机可读存储介质中，处理器从所述计算机可读存储介质读取并执行所述计算机指令，以实现如权利要求1至17任一项所述的方法，或者实现如权利要求18至32任一项所述的方法。
PCT/CN2022/093968 2022-05-19 2022-05-19 无线通信方法、装置、设备、存储介质及程序产品 WO2023221059A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/093968 WO2023221059A1 (zh) 2022-05-19 2022-05-19 无线通信方法、装置、设备、存储介质及程序产品

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2022/093968 WO2023221059A1 (zh) 2022-05-19 2022-05-19 无线通信方法、装置、设备、存储介质及程序产品

Publications (1)

Publication Number Publication Date
WO2023221059A1 true WO2023221059A1 (zh) 2023-11-23

Family

ID=88834312

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/093968 WO2023221059A1 (zh) 2022-05-19 2022-05-19 无线通信方法、装置、设备、存储介质及程序产品

Country Status (1)

Country Link
WO (1) WO2023221059A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200367093A1 (en) * 2018-02-15 2020-11-19 Telefonaktiebolaget Lm Ericsson (Publ) Wireless Device, Radio Network Node and Methods Performed Therein
CN113268920A (zh) * 2021-05-11 2021-08-17 西安交通大学 一种基于联邦学习的无人机群感知数据安全共享方法
CN113950019A (zh) * 2020-07-17 2022-01-18 华为技术有限公司 一种资源调度方法、通信装置及系统
CN114071564A (zh) * 2020-08-05 2022-02-18 大唐移动通信设备有限公司 用户终端与网络进行通信的方法、终端、网络设备及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200367093A1 (en) * 2018-02-15 2020-11-19 Telefonaktiebolaget Lm Ericsson (Publ) Wireless Device, Radio Network Node and Methods Performed Therein
CN113950019A (zh) * 2020-07-17 2022-01-18 华为技术有限公司 一种资源调度方法、通信装置及系统
CN114071564A (zh) * 2020-08-05 2022-02-18 大唐移动通信设备有限公司 用户终端与网络进行通信的方法、终端、网络设备及装置
CN113268920A (zh) * 2021-05-11 2021-08-17 西安交通大学 一种基于联邦学习的无人机群感知数据安全共享方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
VIVO: "Clarifications on QoS handling for L3 relay", 3GPP DRAFT; S2-2107460, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG2, no. E (e-meeting); 20211018 - 20211022, 11 October 2021 (2021-10-11), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP052062334 *

Similar Documents

Publication Publication Date Title
WO2020073855A1 (zh) 建立会话的方法和装置以及发送报文的方法和装置
CN109076347B (zh) 网络切片操作
TWI688231B (zh) ProSe通訊優先處理
WO2020200066A1 (zh) 获取数据包延迟参数的方法、系统和装置
WO2022126563A1 (zh) 网络资源选择方法、终端设备和网络设备
WO2014063568A1 (zh) 缓存状态报告发送与接收方法、用户设备和基站
WO2022033558A1 (zh) 一种中继管理方法及通信装置
WO2021218888A1 (zh) 通信方法和装置
WO2020150876A1 (zh) 会话建立方法、终端设备和网络设备
JP7389243B2 (ja) ＱｏＳマッピング
WO2022012468A1 (zh) 路由配置方法及装置
WO2022052851A1 (zh) 一种服务质量QoS的监测方法
US20220263879A1 (en) Multicast session establishment method and network device
WO2022012361A1 (zh) 一种通信方法及装置
WO2021115429A1 (zh) 一种通信方法及装置
US20230189054A1 (en) Relay communication method, and communication apparatus
WO2023000884A1 (zh) 多播会话处理方法、网络功能实体、装置及存储介质
WO2023221059A1 (zh) 无线通信方法、装置、设备、存储介质及程序产品
WO2023060409A1 (zh) 感知控制方法、装置、设备、系统及存储介质
WO2022151262A1 (zh) 非连续接收配置方法、通信装置及通信系统
WO2022222748A1 (zh) 中继通信方法和装置
WO2023184193A1 (zh) 无线通信方法、装置、设备、存储介质及程序产品
WO2023061207A1 (zh) 一种通信方法、通信装置及通信系统
WO2022021142A1 (zh) QoS参数的设置方法、装置、通信设备及存储介质
WO2023020046A1 (zh) 一种通信方法及通信装置