Communication method, communication apparatus, storage medium and program product

Abstract

Provided are a communication method, a communication apparatus, a storage medium and a program product. The method comprises: determining that an apparatus for providing a communication service to a terminal is switched from a first communication apparatus to a second communication apparatus; and sending a first message, wherein the first message is used for requesting that an apparatus for providing a computing service to the terminal is switched from the first communication apparatus to the second communication apparatus, or the first message is used for requesting that the first communication apparatus and the second communication apparatus cooperatively provide the computing service. In this way, when an apparatus for providing a communication service changes, there is an apparatus for continuing providing a computing service to the terminal, for example, a second communication apparatus continues providing the computing service to the terminal, or a first communication apparatus and the second communication apparatus cooperatively provide the computing service to the terminal, so as to ensure the continuity of the computing service.

Description

Communication methods, communication devices, storage media and software products

[0001] This application claims priority to Chinese Patent Application No. 202411458010.X, filed on October 17, 2024, entitled "Communication Method, Communication Device, Storage Medium and Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, and in particular to communication methods, communication devices, storage media, and program products. Background Technology

[0003] With the development of wireless communication technology, radio access network (RAN) equipment can not only provide communication services to terminals, but also computing services. This helps to reduce the computational load and power consumption of terminals.

[0004] In scenarios where RAN equipment provides computing services to terminals, the RAN equipment providing communication services may change when the terminal moves, making it difficult to guarantee the continuity of computing services. Summary of the Invention

[0005] This application provides communication methods, communication devices, storage media, and program products to ensure the continuity of computing services in scenarios where RAN equipment provides computing services to terminals.

[0006] In a first aspect, this application provides a communication method that can be executed by a first communication device. The first communication device can be an access network device, a component configured in the access network device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing all or part of the functions of the access network device. This application does not limit the scope of the method.

[0007] The first communication device mentioned above can be considered as the source device providing communication services to the terminal, or the device that provides communication services to the terminal before the communication service switch. The second communication device described below can be considered as the target device providing communication services to the terminal, or the device that provides communication services to the terminal after the communication service switch. In other words, the method provided in this application can be applied to scenarios where the device providing communication services to the terminal switches from the first communication device to the second communication device.

[0008] For example, the method includes: determining that the device providing communication services to the terminal is switched from a first communication device to a second communication device; sending a first message, the first message requesting that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requesting that the first communication device and the second communication device cooperate to provide computing services.

[0009] In the above scheme, the device that provides communication services to the terminal can also provide computing services to the terminal. When it is determined that the device that provides communication services to the terminal is switched from the first communication device to the second communication device, the first communication device can request to switch the computing service to the second communication device as well, or request that the first communication device and the second communication device cooperate to provide computing services, so that when the device that provides communication services changes, there is a device that continues to provide computing services to the terminal, such as the second communication device continuing to provide computing services to the terminal or the first communication device and the second communication device cooperating to provide computing services to the terminal, thereby ensuring the continuity of computing services.

[0010] Secondly, this application provides a communication method that can be executed by a second communication device. The second communication device can be an access network device, a component configured in the access network device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing all or part of the functions of the access network device. This application does not limit the scope of the method.

[0011] For example, the method includes: receiving a first message, the first message requesting that the device providing computing services to the terminal switch from a first communication device to a second communication device, or the first message requesting that the first communication device and the second communication device cooperate to provide computing services, wherein the first communication device is the device that provides communication services to the terminal before the communication service switch, and the second communication device is the device that provides communication services to the terminal after the communication service switch.

[0012] In the above scheme, the device that provides communication services to the terminal can also provide computing services to the terminal. In the scenario where the device that provides communication services to the terminal is switched from the first communication device to the second communication device, the first communication device can request to switch the computing service to the second communication device as well, or request that the first communication device and the second communication device work together to provide computing services, so that when the device that provides communication services changes, there is a device that continues to provide computing services to the terminal, such as the second communication device continuing to provide computing services to the terminal or the first communication device and the second communication device working together to provide computing services to the terminal, thereby ensuring the continuity of computing services.

[0013] In some possible implementations of the first and second aspects, the first message indicates one or more of the following: the application (APP) corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the quality of service (QoS) requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

[0014] The applications, models, or functions corresponding to the aforementioned computing services enable the second communication device to clearly identify which one or more applications, models, or functions' computing tasks need to be migrated. The execution progress of the aforementioned computing tasks allows the second communication device to execute computing tasks accordingly, ensuring the continuity of computing tasks and helping to avoid duplicate or interrupted execution. The aforementioned computing resource requirements enable the second communication device to clearly define its computing resource needs, facilitating an assessment of its ability to provide the aforementioned computing services. The QoS requirement information corresponding to the aforementioned computing services helps ensure the quality of service when the second communication device provides computing services. The aforementioned computing task orchestration information can refer to the devices executing computing tasks and the execution order of computing tasks in a distributed computing scenario. For example, in a scenario where a terminal and a second communication device collaboratively execute computing tasks, the computing task orchestration information could specify which part the terminal executes and which part the second communication device executes, thereby ensuring the efficiency and reliability of computing task execution. The aforementioned computing task execution logic can refer to the specific operational flow of the computing task. For example, the terminal executes one part and sends the calculation result to the second communication device, which then executes another part based on the calculation result, ensuring the computing task is executed smoothly according to the execution logic, thus guaranteeing the efficiency and reliability of the computing task.

[0015] In some possible implementations of the first and second aspects, the aforementioned first message also indicates a cooperative processing method.

[0016] By instructing collaborative processing methods, the advantages of distributed computing can be fully utilized to improve computational efficiency, overall system performance, and reliability. For example, different personalized models and data on different devices can be fully utilized to ensure a smooth switch between computing services, avoiding service inconsistencies caused by significant model / data differences after the switch, such as in video generation tasks. Furthermore, different collaborative processing methods can also help balance the load.

[0017] In some possible implementations of the first and second aspects, the above-mentioned collaborative processing methods include one or more of the following: federated learning, data augmentation, model output fusion, model splitting training or inference.

[0018] By specifying one or more of the above-mentioned collaborative processing methods, it is beneficial to improve the flexibility of collaboration.

[0019] In some possible implementations of the first and second aspects, the method further includes: the second communication device sending a second message, and correspondingly, the first communication device receiving the second message; when the first message requests a switch of computing services from the first communication device to the second communication device, the second message indicates agreement to the switch of computing services from the first communication device to the second communication device, or the second message indicates disagreement to the switch of computing services from the first communication device to the second communication device; or, when the first message requests the first and second communication devices to cooperate in providing computing services, the second message indicates agreement to the first and second communication devices to cooperate in providing computing services, or the second message indicates disagreement to the first and second communication devices to cooperate in providing computing services.

[0020] The aforementioned second message can be considered a response to the first message. Feedback from the second communication device helps improve the reliability of the computing service. For example, if the second communication device cannot provide computing services, but the first communication device believes that the second communication device can provide computing services, or if the second communication device has not reserved resources to provide computing services, then feeding back the second message helps improve the reliability of the computing service.

[0021] In some possible implementations of the first and second aspects, when the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating in providing computing services, the second message indicates any of the following: switching computing service mode, reselecting the target device, providing computing services by the terminal, or providing computing services by the terminal and the cloud server.

[0022] The second communication device can be considered as an example of a target device, and reselecting a target device can be understood as selecting a device other than the second communication device as the target device.

[0023] Thus, when the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first and second communication devices cooperating to provide computing services, the second communication device can provide feedback on either of the above, which helps to improve the flexibility of feedback.

[0024] It is understood that when the second message indicates agreement to switch the computing service from the first communication device to the second communication device, or when the second message indicates agreement to cooperate between the first and second communication devices in providing computing services, the second communication device may send back a first acknowledgement (ACK). In one possible implementation, the first ACK and the second ACK may be carried in the same signaling, wherein the second ACK is used to indicate agreement to switch the communication service from the first communication device to the second communication device, but this should not constitute any limitation on this application, and the two may also be carried in different signaling, which this application does not limit.

[0025] In some possible implementations of the first and second aspects, the above method further includes: a first communication device sending context information, and correspondingly, a second communication device receiving the context information, which indicates one or more of the following: an application corresponding to the computing service, a model corresponding to the computing service, a function corresponding to the computing service, computing data, or an execution log of a computing task.

[0026] By leveraging contextual information, the first and second communication devices can collaborate more effectively, reducing redundant work and improving execution efficiency. For example, the application, model, or function corresponding to the computing service can enable the second communication device to determine which application, model, or function needs to be migrated. The first communication device instructs on computational data, which can be raw input data, intermediate output data, or other auxiliary data, etc. This application does not limit this; instructing on computational data helps improve computational efficiency. The execution log of the computing task helps the second communication device track the execution status, progress, and historical records of the computing task, thus contributing to improved execution efficiency.

[0027] In some possible implementations of the first and second aspects, the method further includes: a first communication device sending a third message, and correspondingly a second communication device receiving the third message, the third message requesting a switch of communication service from the first communication device to the second communication device; the second communication device sending a fourth message, and correspondingly the first communication device receiving the fourth message indicating agreement to switch the communication service from the first communication device to the second communication device.

[0028] In this way, when the first communication device determines that the communication service is switched from the first communication device to the second communication device, it can send a request to the second communication device. Accordingly, the second communication device responds to the request to ensure that the second communication device can provide communication services to the terminal when the terminal switches to the second communication device, thereby improving the continuity of communication services and thus improving the user experience.

[0029] In a first possible implementation, the first communication device requests a switch in communication services while simultaneously requesting a switch in computing services, or requests the first and second communication devices to collaboratively provide computing services. As an example and not a limitation, the first communication device sends a third message and a first message; correspondingly, the second communication device receives both the third and first messages. The first and third messages may be carried in the same signaling message or in different signaling messages; this application does not limit this.

[0030] In a second possible implementation, the first communication device requests a switch to a communication service, and, if preset conditions are met, requests a switch to a computing service or requests the first and second communication devices to cooperate in providing computing services.

[0031] As an example and not a limitation, the first communication device sending a first message includes: meeting preset conditions and sending the first message, the preset conditions including one or more of the following: completing a historical calculation task; the time elapsed since the third message was sent has reached a first duration; and the terminal triggers the first communication device to send the first message.

[0032] When the first communication device sends a first message under preset conditions, it helps ensure load balancing for the second communication device. For example, if multiple first communication devices request to switch computing services to the same second communication device after determining that their communication services have switched from the first device to the same second device, the load on the second communication device will increase rapidly, potentially leading to its failure. By requesting to switch computing services only when the preset conditions are met, it avoids the simultaneous switching of computing services from multiple first communication devices to the same second communication device, thus ensuring load balancing for the second communication device. Secondly, it helps ensure the timeliness of computing tasks and data privacy. For example, if the first communication device completes a historical computing task before switching, it ensures that the historical computing task is processed promptly without being transmitted to the second communication device, thus protecting data privacy. Thirdly, it helps ensure the accuracy of computing tasks. For example, in scenarios where the model deployed on the first communication device has better performance, requesting to switch only after the preset conditions are met can improve the accuracy of the current computing task.

[0033] In the second possible implementation described above, the third message may indicate the switching time for the computing service.

[0034] By including the switching time of the computing service in the request to switch the communication service, the second communication device can reserve computing resources for it, so as to ensure that the computing service can also be switched to the second communication device, thereby improving the continuity of the computing service.

[0035] In the second possible implementation described above, the method further includes: a first communication device sending a fifth message, and correspondingly, a second communication device receiving the fifth message, the fifth message indicating the forwarding settings of the computing task, the forwarding settings including one or more of the following: a forwarding path, the address of each node on the forwarding path or the identifier of the data stream, the forwarding path including the first communication device and the second communication device.

[0036] In other words, before the communication service switches to the second communication device but the computing service switches to the second communication device, that is, in the scenario where the second communication device provides the communication service and the first communication device provides the computing service, the first communication device can instruct the forwarding settings of the computing task. The forwarding path in the forwarding settings includes the first communication device and the second communication device. In other words, the first communication device performs the computing task, and its computing result needs to be forwarded to the terminal by the second communication device, or the uplink computing data of the terminal needs to be forwarded to the first communication device by the second communication device so that the first communication device can perform the computing task.

[0037] In one possible implementation, the second communication device also sends a sixth message to the core network device, which indicates one or more of the following: a forwarding path, the addresses of the nodes on the forwarding path, the identifier of the data flow, or indication information indicating that the task session identifier and / or the QoS flow identifier corresponding to the computing service remain unchanged.

[0038] The second communication device instructs the core network equipment on the above content. When the core network equipment sends downlink computing data, it can do so based on the above content. This avoids the core network equipment mistakenly believing that the computing service has also switched to the second communication device when the communication service has switched to the second communication device, thereby improving the reliability of the system.

[0039] In some possible implementations of the first and second aspects, the first communication device sends the first message before receiving the fourth message. For the second communication device, the first message is received before the fourth message is sent.

[0040] In other words, the first message is sent before the response message to the communication service switching request. In other words, if the communication service switching is not completed, requesting a switching of the computing service in a timely manner helps reduce the possibility of computing service interruption and thus ensures user experience.

[0041] In some possible implementations of the first and second aspects, the second communication device also sends a seventh message to the core network equipment, which instructs modification of the forwarding path of the data stream.

[0042] In other words, when the computing service is switched from the first communication device to the second communication device, the second communication device can instruct the core network equipment to modify the forwarding path of the data stream. This allows the core network equipment to determine the forwarding path of the downlink computing data based on the aforementioned seventh message, thus improving system reliability.

[0043] Thirdly, this application provides a communication method that can be executed by a terminal device. The terminal device can be the terminal itself, a component configured in the terminal (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing all or part of the terminal functions. This application does not limit the scope of the method.

[0044] For example, the method includes: receiving first indication information, the first indication information indicating a device for providing computing services to a terminal and / or a computing service switching mode, the computing service switching mode being a switching mode of the device for providing computing services to the terminal when the device for providing communication services to the terminal is switched from a first communication device to a second communication device.

[0045] The aforementioned computing service switching methods can be, for example, synchronous switching, asynchronous switching, or collaborative processing.

[0046] In the above scheme, the terminal can receive instructions on the computing service switching mode and / or instructions from the device providing computing services to the terminal. Instructions from the device providing computing services to the terminal help the terminal determine which device to send computing data to or which device to perform the computing task. Instructions on the computing service switching mode help the terminal determine the decision-making situation regarding the switching of computing services.

[0047] In one possible implementation, the terminal sends first information to the first communication device, which indicates the supported computing service switching mode and / or computing resource requirements. This facilitates the first communication device in deciding on the computing service switching mode and / or determining the computing resource requirements.

[0048] Fourthly, this application provides a communication device that can implement the method described in the first aspect and any possible implementation thereof; or, can implement the method described in the second aspect and any possible implementation thereof; or, can implement the method described in the third aspect and any possible implementation thereof. The device includes corresponding modules for performing the above-described methods. The modules included in the device can be implemented by software and / or hardware.

[0049] The communication device may be a first communication device for implementing the method described in the first aspect and any possible implementation of the first aspect.

[0050] In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the first aspect and any possible implementation of the first aspect. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0051] The communication device may also be a second communication device for implementing the methods described in the second aspect and any possible implementation of the second aspect. In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the second aspect and any possible implementation of the second aspect. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0052] The communication device can also be a terminal device for implementing the methods described in the third aspect and any possible implementation of the third aspect. In one possible implementation, the communication device may include modules or units that perform the methods / operations / steps / actions described in the third aspect and any possible implementation of the third aspect. These modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0053] Fifthly, this application provides a communication device including a processor, which can be used to implement the method described in the first aspect and any possible implementation of the first aspect, or to implement the method described in the second aspect and any possible implementation of the second aspect, or to implement the method described in the third aspect and any possible implementation of the third aspect by executing a computer program in a memory and / or by logic circuitry.

[0054] Optionally, the device further includes a communication interface. The communication interface is used to receive signals from other communication devices outside the device and transmit them to the processor, or to send signals from the processor to other communication devices outside the device. Exemplarily, the communication interface may be a transceiver, circuit, bus, module, pin, or other type of communication interface.

[0055] Optionally, the device further includes a memory. The memory stores program instructions and data. The memory is coupled to the processor, which, when executing the instructions stored in the memory, can implement the methods described in the preceding aspects. Optionally, the memory and the processor are integrated together.

[0056] In a sixth aspect, this application provides a computer-readable storage medium storing a computer program or instructions that, when executed, implement the method described in the first aspect and any possible implementation thereof, or implement the method described in the second aspect and any possible implementation thereof, or implement the method described in the third aspect and any possible implementation thereof.

[0057] In a seventh aspect, this application provides a computer program product comprising instructions which, when executed, implement the method described in the first aspect and any possible implementation thereof, or implement the method described in the second aspect and any possible implementation thereof, or implement the method described in the third aspect and any possible implementation thereof.

[0058] Eighthly, this application provides a chip system including at least one processor for supporting the implementation of the functions involved in the first aspect and any possible implementation of the first aspect, or for supporting the implementation of the functions involved in the second aspect and any possible implementation of the second aspect, or for supporting the implementation of the functions involved in the third aspect and any possible implementation of the third aspect, such as receiving or processing data involved in the above methods.

[0059] In one possible design, the chip system also includes a memory for storing program instructions and data, which may be located within or outside the processor.

[0060] The chip system can consist of chips or include chips and other discrete components.

[0061] Ninthly, this application provides a communication system comprising a first communication device and a second communication device, wherein the first communication device is used to implement the method described in the first aspect and any possible implementation thereof, and the second communication device is used to implement the method described in the second aspect and any possible implementation thereof.

[0062] In one possible implementation, the communication system further includes a terminal device for implementing the method described in the third aspect and any possible implementation of the third aspect.

[0063] It should be understood that the fourth to ninth aspects of this application correspond to the technical solutions of the first to third aspects of this application, and the beneficial effects obtained by each aspect and the corresponding feasible implementation are similar, and will not be repeated here. Attached Figure Description

[0064] Figure 1 is a flowchart illustrating existing methods for ensuring the continuity of computing services;

[0065] Figure 2 is a schematic diagram of the architecture of a communication system applicable to the method provided in the embodiments of this application;

[0066] Figure 3 is another schematic diagram of the architecture of a communication system applicable to the method provided in the embodiments of this application;

[0067] Figure 4 is a schematic flowchart of the communication method provided in an embodiment of this application;

[0068] Figure 5 is a detailed flowchart of the communication method provided in the embodiments of this application;

[0069] Figure 6 is another detailed flowchart of the communication method provided in an embodiment of this application;

[0070] Figure 7 is another detailed flowchart of the communication method provided in the embodiments of this application;

[0071] Figure 8 is a schematic block diagram of a communication device provided in an embodiment of this application;

[0072] Figure 9 is another schematic block diagram of the communication device provided in the embodiments of this application. Detailed Implementation

[0073] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0074] Before introducing the methods provided in the embodiments of this application, the following points should be noted.

[0075] First, in this application, the terms "first" and "second" are used to distinguish identical or similar items with essentially the same function and purpose. For example, "first communication device" and "second communication device" are merely used to distinguish different devices; similarly, "first message," "second message," "third message," etc., are merely used to distinguish different messages and do not limit their order. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and that "first" and "second" do not necessarily imply that they are different.

[0076] Second, in this application, "one or more of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, one or more of a, b, or c can represent: a, b, c; a and b; a and c; b and c; or a and b and c. Where a, b, and c can be single or multiple.

[0077] Third, the method provided in this application can be applied to fourth-generation (4G) communication systems, such as long-term evolution (LTE) communication systems, as well as fifth-generation (5G) communication systems, such as 5G new radio (NR) communication systems, as well as future communication systems, and can also be applied to Bluetooth systems, wireless fidelity (Wi-Fi) systems, long-range (LoRa) Internet of Things (IoT) systems, or vehicle-to-everything (V2X) systems.

[0078] Fourth, in this application, "when...", for example, when the second message indicates disagreement with the switching of the computing service from the first communication device to the second communication device, means that the device will make corresponding processing under certain objective circumstances. It is not a time limit, nor does it require the device to make a judgment action when it implements the action, nor does it mean that there are other limitations.

[0079] Fifth, in this application, "simultaneously" can be understood as at the same point in time or within a period of time; this application does not limit this. For example, requesting a switch in the computing service at the same time as requesting a switch in the communication service can be understood as sending the switch request for the communication service and the switch request for the computing service at the same point in time, or it can be understood as sending the switch request for the communication service and the switch request for the computing service within a period of time. The aforementioned time period can be understood in conjunction with the context. For example, in this application, the aforementioned time period can be less than or equal to the time interval between sending the switch request for the communication service and receiving the response to the switch request for the communication service.

[0080] Sixth, in this application, communication between different devices can refer to direct communication between different devices (i.e., without the need for relaying or forwarding by other devices), or communication between different devices through other devices (i.e., requiring relaying or forwarding by other devices), or communication between a functional unit within a device and other devices through another functional unit. For example, when a first communication device sends context information to a second communication device, it can mean that the service unit (SU) of the first communication device directly sends the context information to the SU of the second communication device, or it can mean that the SU of the first communication device sends the context information through another functional unit of the first communication device, and the other functional unit of the second communication device receives the context information and forwards it to the SU of the second communication device.

[0081] In existing systems, computing services can be offloaded from the terminal to the edge. In other words, computing resources can be deployed at the network edge (such as after the access network) to provide computing services to the terminal, thereby reducing the terminal's computational load and power consumption. For example, a computing server can be deployed after the access network to provide computing services to the terminal.

[0082] In the above scenario, the terminal may move, causing the base station providing communication services to change. In this case, there is already a method to ensure the continuity of computing services. It will be described in detail below with reference to Figure 1.

[0083] Figure 1 is a flowchart illustrating existing methods for ensuring the continuity of computing services.

[0084] As shown in Figure 1, in step 101, mobile edge computing (MEC) server 1 and MEC server 2 exchange MEC capability information.

[0085] For example, MEC server 1 and MEC server 2 can interact with one or more of the information, computing power, and computing load of the deployed model.

[0086] In step 102, the source base station sends a handover request, which requests a switchover of the base station providing communication services to the terminal from the source base station to the target base station. The handover request carries a local processing instruction, which indicates the data stream that needs to be processed by the MEC server and which MEC server should process it. Accordingly, the target base station receives the handover request.

[0087] In step 103, the target base station sends a handover response, and the source base station receives the handover response accordingly. This handover response indicates whether the user agrees to the handover of communication services from the source base station to the target base station.

[0088] In step 104, the source base station sends a radio resource control (RRC) configuration message to the terminal. Correspondingly, the terminal receives the aforementioned RRC configuration message.

[0089] The aforementioned RRC configuration message can also be referred to as RRC connection reconfiguration, and this application does not limit this name.

[0090] The aforementioned RRC configuration message may include one or more of the following: information about the target base station (such as the physical cell identity (PCI) and frequency information of the target cell), handover parameters (such as handover time), resource configuration (such as time and frequency resources allocated by the target base station to the terminal), or security information (such as the key used for encryption and integrity protection after handover). This application does not limit its scope.

[0091] In step 105, the terminal performs the random access channel (RACH) procedure.

[0092] For example, the RACH process includes: the terminal generating and sending a random access preamble to the target base station; the target base station sending a random access response; after receiving the random access response, the terminal sending an RRC connection request; the target base station receiving the RRC connection request and sending an RRC connection setup message; and the terminal receiving the RRC connection setup message. Further, the terminal sends an RRC connection setup complete message to notify the target base station that the RRC connection has been successfully established. After successfully establishing an RRC connection with the target base station, the terminal sends a handover complete message to the target base station to notify the target base station that the handover process has been completed.

[0093] In step 106, the target base station sends a path switch request to the core network equipment (such as access and mobility management function (AMF) network elements).

[0094] For computing services, one possible scenario is that the computing service is switched from MEC server 1 corresponding to the source base station to MEC server 2 corresponding to the target base station. In this case, the data flow does not pass through the source base station but passes through the target base station. As shown in step 107, for downlink data flow, the core network equipment sends downlink data to the target base station. The target base station determines whether it needs to forward the data to MEC server 2 for computing based on the local processing indication of the packet data unit (PDU) session / data radio bearer (DRB) / QoS flow (i.e., the local processing indication in step 102). For example, if the local processing indication is used to indicate that the computing is performed by MEC server 2 corresponding to the target base station, then the target base station forwards the downlink data to MEC server 2. MEC server 2 performs the computing and sends the computing result to the target base station. The target base station then sends the computing result to the terminal.

[0095] Another possible scenario is that the communication service is switched from the source base station to the target base station, but the computing service is still performed by the MEC server 1 corresponding to the source base station. In this case, the data flow passes through the source base station and the target base station. As shown in step 108, for the downlink data flow, the core network equipment sends downlink data to the target base station, the target base station sends downlink data to the source base station, the source base station sends downlink data to MEC server 1, MEC server 1 performs the calculation, and then sends the calculation result to the target base station through the source base station. The target base station then sends the calculation result to the terminal.

[0096] With the development of wireless communication technology, RAN equipment (such as base stations) can provide not only communication services to terminals but also computing services. This can reduce the computational load and power consumption of terminals. In scenarios where RAN equipment provides computing services to terminals, the RAN equipment providing communication services may change when the terminal moves, making it difficult to guarantee the continuity of computing services.

[0097] In view of this, this application provides a communication method in a scenario where a device providing communication services to a terminal can also provide computing services to the terminal. When it is determined that the device providing communication services to the terminal is switched from a first communication device to a second communication device, the first communication device may request that the computing service also be switched to the second communication device, or request that the first communication device and the second communication device cooperate to provide computing services. This ensures that when the device providing communication services is switched, there is a device that continues to provide computing services to the terminal, such as the second communication device continuing to provide computing services to the terminal or the first communication device and the second communication device cooperating to provide computing services to the terminal, thereby ensuring the continuity of computing services.

[0098] Before describing the communication method provided in this application in detail, the system architecture applicable to this application will be described below with reference to Figure 2.

[0099] Figure 2 is a schematic diagram of the architecture of a communication system applicable to the method provided in the embodiments of this application. The application scenarios applicable to this application are illustrated using the communication system architecture shown in Figure 2 as an example. Figure 2 shows a possible, non-limiting system schematic diagram. As shown in Figure 2, the communication system 1000 includes a RAN 100 and a core network (CN) 200. The RAN 100 includes at least one access network device (110a and 110b in Figure 2, collectively referred to as 110) and at least one terminal (120a-120j in Figure 2, collectively referred to as 120). The RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 2). The terminal 120 is wirelessly connected to the access network device 110. The access network device 110 is connected to the core network 200 wirelessly or via a wired connection. The core network equipment in the core network 200 and the access network equipment 110 in the RAN 100 can be different physical devices, or they can be the same physical device that integrates core network logical functions and radio access network logical functions.

[0100] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future communication systems. RAN 100 can also be an open access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a Wi-Fi system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0101] It is understood that Figure 2 only shows one possible communication system architecture that can be applied to the embodiments of this application, and other devices may also be included in the communication system architecture in other possible scenarios.

[0102] Access network device 110 is used to help terminals achieve wireless access. Multiple access network devices 110 in communication system 1000 can be nodes of the same type or different types. In some scenarios, the roles of access network device 110 and terminal 120 are relative. For example, network element 120i in Figure 2 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; but for base station 110a, network element 120i is a terminal. Access network device 110 and terminal 120 are sometimes referred to as communication devices. For example, network elements 110a and 110b in Figure 2 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0103] In one possible scenario, access network equipment can be a base station, an evolved NodeB (eNodeB), a transmitting and receiving point (TRP), a transmitting point (TP), a next-generation NodeB (gNB), a base station in a future mobile communication system, a satellite, or an access point (AP) in a Wi-Fi system, an integrated access and backhaul (IAB) node, or an access network device in a mobile switching center non-terrestrial network (NTN) communication system, i.e., it can be deployed on a high-altitude platform or satellite, etc. Access network equipment can be a macro base station (as shown in Figure 2, 110a), a micro base station or indoor station (as shown in Figure 2, 110b), a relay node or donor node, or a radio controller in a CRAN scenario. Access network equipment can also function as a base station in device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, drone communication, and machine-to-machine (M2M) communication. Optionally, the access network equipment can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU).

[0104] In another possible scenario, multiple access network devices collaborate to assist terminals in achieving wireless access, with each device performing a portion of the base station's functions. For example, access network devices can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs). CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio equipment or radio units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). It is understood that access network devices can be CU nodes, DU nodes, or devices comprising both CU and DU nodes. Furthermore, CUs can be classified as access network devices within the RAN (RAN) or the CN (CN), without limitation.

[0105] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0106] In this embodiment, the form of the access network device is not limited. The device used to implement the function of the access network device can be the access network device itself; or it can be a device that supports the access network device in implementing the function, such as a chip system. The device can be installed in the access network device or used in conjunction with the access network device.

[0107] A terminal can also be called a terminal device, user equipment (UE), mobile station (MS), mobile terminal (MT), etc., or a device used to provide voice or data connectivity to users, and can also be an Internet of Things (IoT) device. For example, terminals include handheld devices with wireless connectivity, vehicle-mounted devices, etc. Currently, terminals can include, for example: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices (such as smartwatches, smart bracelets, pedometers, smart glasses, etc.), in-vehicle equipment (such as cars, bicycles, electric vehicles, airplanes, ships, trains, high-speed trains, etc.), satellite terminals, virtual reality (VR) devices, augmented reality (AR) devices, point of sale (POS) machines, customer-premises equipment (CPE), light user equipment (UE), reduced capability user equipment (REDCAP UE), wireless terminals in industrial control, smart home devices (such as refrigerators, televisions, air conditioners, electricity meters, etc.), smart robots, robotic arms, workshop equipment, wireless terminals in autonomous driving, wireless terminals in smart healthcare, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, or wireless terminals in smart homes, and flying equipment (such as smart robots, hot air balloons, drones, airplanes), etc. The terminal can also be a vehicle device, such as a vehicle unit, vehicle module, vehicle chip, on-board unit (OBU), or telematics box (T-BOX). The terminal can also be other devices with terminal functions. For example, the terminal can also be a device that plays the role of a terminal in D2D communication.

[0108] The embodiments of this application do not limit the device form of the terminal. The device used to implement the functions of the terminal can be the terminal itself; it can also be a device that supports the terminal in implementing the functions, such as a chip system. The device can be installed in the terminal or used in conjunction with the terminal. In the embodiments of this application, the chip system can be composed of chips or can include chips and other discrete devices.

[0109] In addition, access network equipment and terminals can be equipped with multiple antennas or a single antenna; this application does not limit this.

[0110] Figure 3 is another schematic diagram of the architecture of a communication system applicable to the method provided in the embodiments of this application.

[0111] As shown in Figure 3, computing resources are deployed in the application's cloud server (referred to as the application server in the figure), access network devices, and terminals. The scenario shown in Figure 3 is a switch of the terminal from the source access network device to the target access network device; that is, a switch occurs in the access network device providing communication services to the terminal. The following will describe each device in detail.

[0112] The access network equipment includes CU / DU and SU, where the SU provides computing services. The SU and CU / DU communicate via the Nx interface. SUs can communicate directly or via forwarding through the access network equipment; this application does not limit this. Access network equipment communicates with each other via the Xn interface. Access network equipment and core network equipment communicate via next-generation (NG) interfaces.

[0113] Before a terminal switches from a source access network device to a target access network device, the source access network device can provide not only communication services but also computing services to the terminal. Taking downlink data as an example, the application's cloud server sends downlink data to the core network device. The core network device sends the downlink data to the source access network device through the NG interface. The CU / DU in the source access network device outputs the downlink data to the SU in the source access network device. The SU performs the computing task and sends the computing result to the terminal through the source access network device.

[0114] The communication method provided in this application will be described in detail below with reference to the accompanying drawings. The following description uses the interaction between a first communication device and a second communication device as an example to illustrate the communication method provided in this application, but this should not be construed as limiting the scope of this application. The first communication device may also be replaced by a component configured in the first communication device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing all or part of the functions of the first communication device. The second communication device may be replaced by a component configured in the second communication device (such as a chip, chip system, processor, etc.), or a logic module or software capable of implementing all or part of the functions of the second communication device.

[0115] The first and second communication devices mentioned above can be access network devices. For example, the first communication device can be a source access network device (such as a source base station), and the second communication device can be a target access network device (such as a target base station). Applicable scenarios include, for example, when a base station providing communication services to a terminal switches from a source access network device to a target access network device.

[0116] Figure 4 is a schematic flowchart of the communication method 400 provided in an embodiment of this application. The steps of method 400 are described in detail below.

[0117] In step 410, the device that the first communication device determines to provide communication services to the terminal is switched from the first communication device to the second communication device.

[0118] Taking a base station as an example, exemplarily, the source base station determines that the base station providing communication services to the terminal is switched to the target base station; that is, the terminal's serving base station is switched from the source base station to the target base station. For example, the source base station can determine the target base station based on measurement results sent by the terminal; that is, the device providing communication services to the terminal is switched from the source base station to the target base station. The measurement results include information such as the signal quality of the target base station. This process is the same as existing technologies and will not be described in detail here.

[0119] It is understood that the device for providing communication services to the terminal, as determined by the first communication device, switches from the first communication device to the second communication device. Specifically, this could be the CU / DU in the first communication device switching from the first communication device to the second communication device, or it could be other modules; this application does not limit this. In the ORAN system, specifically, this could be the O-CU / O-DU in the first communication device switching from the first communication device to the second communication device, or it could be other modules.

[0120] In step 420, the first communication device sends a first message requesting that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requests that the first communication device and the second communication device cooperate to provide computing services. Accordingly, the second communication device receives the aforementioned first message.

[0121] In this context, computing services can be understood as services provided by a device that offer computing resources and capabilities. In this application, access network devices, terminals, cloud servers, etc., can all provide computing services.

[0122] One possible implementation is that, if the first communication device determines that the device providing communication services to the terminal is switching from the first communication device to the second communication device, the first communication device can send a first message to request that the device providing computing services to the terminal also switch from the first communication device to the second communication device, or to request that the first and second communication devices collaboratively provide computing services. In this way, in scenarios where the device providing communication services to the terminal switches, there is a possibility that a device can continue to provide computing services to the terminal, such as the second communication device continuing to provide computing services or the first and second communication devices collaboratively providing computing services to the terminal, thereby ensuring the continuity of computing services.

[0123] As an example, if the first communication device determines that the device providing communication services to the terminal is switched from the first communication device to the second communication device, the first communication device may send a first message to request that the device providing computing services to the terminal also be switched from the first communication device to the second communication device.

[0124] The switching requests for communication services from the first communication device to the second communication device (denoted as Switching Request 1) and the switching requests for computing services from the first communication device to the second communication device (denoted as Switching Request 2) can be synchronous (i.e., the communication service and computing service switch synchronously) or asynchronous (i.e., the communication service and computing service switch asynchronously), and this application does not limit the specifics. The synchronous nature of Switching Request 1 and Switching Request 2 can be understood as the first communication device sending Switching Request 1 and Switching Request 2 simultaneously, or the Switching Request 1 and Switching Request 2 can be carried in the same signaling, or the Switching Request 1 and Switching Request 2 can be transmitted on the same time-frequency resource. "Simultaneously" can be understood as the same point in time or within a certain time period, and this application does not limit the specifics. For example, sending Switching Request 2 at the same time as sending Switching Request 1 can be understood as sending at the same point in time or within a certain time period. The time period can be understood in context; for example, in this application, the time period can be less than or equal to the time interval between sending Switching Request 1 and receiving the response message of Switching Request 1. The handover request 1 and handover request 2 are asynchronous. This can be understood as the first communication device sending handover request 1, and then sending handover request 2 if the preset conditions are met. For details on the specific implementation of synchronous and asynchronous handover, please refer to the following text, which will not be elaborated here.

[0125] In another example, if the first communication device determines that the device providing communication services to the terminal is switched from the first communication device to the second communication device, the first communication device may send a first message to request that the first communication device and the second communication device cooperate to provide computing services. That is, the first communication device may request that the first communication device and the second communication device cooperate to provide computing services to the terminal.

[0126] In one possible implementation, the first message indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

[0127] In this context, "computing service" refers to an application that supports the development, operation, or maintenance of an application by providing computing services (such as computing resources and capabilities). "Model" refers to a model that supports training or inference by providing computing services. "Function" refers to a function that is accomplished by providing computing services. It's understandable that the same function can be accomplished by one or more models, or multiple models can perform the same function. The following will use a personal assistant (an example of an application) as an example to describe the relationship between application, model, and function in detail.

[0128] For example, a personal assistant can be viewed as an application. A first communication device can request that the computing services of this application be provided by a second communication device, or that the first and second communication devices cooperate in providing such services. The personal assistant can create a personal plan, which may involve multiple functions, such as natural language processing, creating a personal plan based on user or environmental information, and feeding the personal plan back to the terminal (involving language generation). The first communication device can request that the computing services of at least one of these functions be provided by the second communication device, or that the first and second communication devices cooperate in providing such services. Each function may require one or more models; the first communication device can request that the computing services of at least one of these models be provided by the second communication device, or that the first and second communication devices cooperate in providing such services.

[0129] In one possible implementation, the first message can indicate the identifier of the application, model, or function corresponding to the computing service. This allows the second communication device to clearly identify which one or more applications, models, or functions' computing tasks need to be migrated.

[0130] A computational task refers to one or more tasks performed using computational resources. If a device can provide computational services, then that device can perform computational tasks. For example, to complete a certain function, computational resources are needed to perform one or more tasks. Similarly, training or inference of a model requires the use of computational resources to perform one or more tasks. In one possible implementation, the aforementioned computational tasks are artificial intelligence (AI) computational tasks.

[0131] Computing resources refer to the collection of various hardware and software resources used to perform computing tasks. As an example, and not a limitation, the type of computing resources can indicate the type of hardware used to perform the computing tasks, such as a central processing unit (CPU), a graphics processing unit (GPU), a neural processing unit (NPU), and memory. This memory can include, but is not limited to, at least one of random access memory (RAM) or read-only memory (ROM). The size of computing resources can be measured by one or more of the following: millions of instructions per second (MIPS), dhrystone million instructions executed per second, operations per second (OPS), floating-point operations per second (FLOPS), or hashes per second (Hash / s), etc.

[0132] The execution progress of the aforementioned computational task can refer to how much of the computational task has been completed, and / or how much of the computational task remains. Based on this, the second communication device executes the computational task to ensure its continuity and avoid duplicate or interrupted execution.

[0133] The aforementioned computing resource requirements may refer to the type and / or size of computing resources required, which is not limited in this application. The first message indicates the computing resource requirements so that the second communication device can assess whether it can provide the aforementioned computing services.

[0134] The QoS requirements for the aforementioned computing services refer to the quality of service that needs to be guaranteed when providing computing services. For example, the QoS requirements for the aforementioned computing services include requirements for model accuracy, latency, communication and computing capabilities, and data requirements, etc.

[0135] The aforementioned task orchestration information can refer to the objects executing the tasks and the execution order of the tasks in a distributed computing scenario. For example, in a scenario where a terminal and a second communication device collaborate to execute a task, the task orchestration information could be which part the terminal executes, which part the second communication device executes, etc., in order to ensure the efficiency and reliability of the task execution.

[0136] The execution logic of the aforementioned computing task can refer to the specific operation process of the computing task. For example, the terminal executes a part and sends the computing result to the second communication device, and the second communication device executes another part based on the computing result. This ensures that the computing task is executed smoothly according to the execution logic, thereby ensuring the efficiency and reliability of the computing task.

[0137] In one possible implementation, the first communication device obtains the identifier of the application corresponding to the computing service, the identifier of the model corresponding to the computing service, the identifier of the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task, and then sends a first message to carry one or more of the above. For example, the CU / DU in the first communication device indicates that the communication service of the SU (denoted as the first SU) in the first communication device is about to be switched from the first communication device to the second communication device, and the first SU indicates one or more of the above parameters to the CU / DU in the first communication device. The CU / DU in the first communication device and the first SU can interact through the Nx interface.

[0138] In one possible implementation, the aforementioned first message also indicates the collaborative processing method.

[0139] One possible scenario is that a first message requests a first communication device and a second communication device to collaboratively provide computing services. In this case, the first message also indicates the collaborative processing method, instructing the second communication device on how to collaboratively provide computing services. This helps to fully leverage the advantages of distributed computing, improving computing efficiency, overall system performance, and reliability. For example, by having the first and second communication devices collaboratively provide computing services, the different personalized models deployed on the first and second communication devices can be fully utilized to improve the execution quality and efficiency of computing tasks. Furthermore, collaboration between the first and second communication devices, rather than the second communication device providing computing services entirely, facilitates a smoother switching of computing services, avoiding inconsistencies in service experience due to large model / data differences after the switch, such as in video generation tasks, thus improving user experience. Moreover, different collaborative processing methods can also help balance the load on the devices.

[0140] Another possible scenario is that the first communication device and the third communication device cooperate to provide computing services to the terminal. When it is determined that the device providing communication services to the terminal is switched from the first communication device to the second communication device, the first communication device sends a first message. The first message requests that the device providing computing services to the terminal be switched from the first communication device to the second communication device. At this time, the first message may also indicate the cooperative processing method of the first communication device and the third communication device, so that the second communication device and the third communication device can continue to cooperate to provide computing services to the terminal based on this cooperative processing method.

[0141] In one possible implementation, the above-mentioned collaborative processing methods include one or more of the following: federated learning, data augmentation, model output fusion, model splitting training or inference.

[0142] In other words, the first communication device can instruct one or more of the above-mentioned collaborative processing methods, which helps to improve the flexibility of collaboration.

[0143] Federated learning, also known as federated training, is a distributed machine learning method that utilizes multiple devices or nodes to collaboratively train a global model. In federated learning, each device (such as a mobile phone or computer) independently trains the model on local data. Then, it sends updates to the model (such as gradients or model parameters) to another device, which aggregates these updates, updates the global model, and then sends the updated global model back to all the other devices. This process can iterate multiple times until the model converges. For example, a first communication device and a second communication device can collaborate on federated learning.

[0144] Data augmentation refers to a situation where one device provides data while another device performs computational tasks. For example, one of a first communication device and a second communication device (taking the first communication device as an example) is responsible for providing data, while the second communication device is responsible for performing computational tasks.

[0145] Model output fusion refers to the process where multiple devices each perform model training and output training results, and one device then merges these training results. For example, if the training of a certain model includes training for indoor scenes and training for outdoor scenes, the first communication device trains for indoor scenes, the second communication device trains for outdoor scenes, and finally the second communication device merges the training results from both scenarios.

[0146] Model split training or inference refers to multiple devices jointly training or inferring a model. For example, a first communication device trains a part of a model, while a second communication device trains another part of the model. For instance, taking a convolutional neural network (CNN) model as an example, the first communication device executes convolutional layers and pooling layers, and sends the intermediate output results to the second communication device. The second communication device then continues to execute the remaining layers, such as activation layers, fully connected layers, normalization layers, and dropout layers.

[0147] In one possible implementation, the method 400 further includes: the second communication device sending a second message, and correspondingly, the first communication device receiving the second message; when the first message requests the computing service to be switched from the first communication device to the second communication device, the second message indicates agreement to switch the computing service from the first communication device to the second communication device, or the second message indicates disagreement to switch the computing service from the first communication device to the second communication device; or, when the first message requests the first communication device and the second communication device to cooperate in providing computing services, the second message indicates agreement to cooperate in providing computing services from the first communication device and the second communication device, or the second message indicates disagreement to cooperate in providing computing services from the first communication device and the second communication device.

[0148] The aforementioned second message can be considered a response message to the first message. Feedback from the second communication device helps improve the reliability of the computing service. For example, if the second communication device cannot provide computing services, but the first communication device believes that the second communication device can provide computing services, or if the second communication device has not reserved resources to provide computing services, then feedback of the response message helps improve the reliability of the computing service.

[0149] One possible scenario is that the first message requests a switch of computing service from the first communication device to the second communication device. The second communication device then sends a second message indicating either agreement to the switch or disagreement with the switch. Accordingly, the first communication device receives the second message.

[0150] Another possible scenario is that the first message requests the first communication device and the second communication device to cooperate in providing computing services. The second communication device then sends a second message to indicate whether it agrees to the first communication device and the second communication device cooperating in providing computing services, or to indicate whether it disagrees with the first communication device and the second communication device cooperating in providing computing services. Accordingly, the first communication device receives the aforementioned second message.

[0151] It is understood that when the second message indicates agreement to switch the computing service from the first communication device to the second communication device, or when the second message indicates agreement to cooperate between the first and second communication devices in providing computing services, the second communication device may send back a first ACK. In one possible implementation, the first ACK and the second ACK may be carried in the same signaling, wherein the aforementioned second ACK is used to indicate agreement to switch the communication service from the first communication device to the second communication device, but this should not constitute any limitation on this application, and the two may also be carried in different signaling, which this application does not limit.

[0152] In one possible implementation, before sending the second message, the second communication device determines the second message based on its own communication status, computing resource status, computing status, and the first message. One possible scenario is that the first message requests a switch of computing service from the first communication device to the second communication device. The second communication device, based on its own communication status, computing resource status, computing status, and the first message, determines whether it can provide computing service to the terminal. As an example, and not a limitation, the CU / DU in the second communication device outputs the first message and related information (such as communication status) to the SU (denoted as the second SU) in the second communication device via the Nx interface. The second SU, based on the communication status, computing resource status, computing status, and the first message, determines whether it can provide computing service to the terminal and feeds back to the CU / DU in the second communication device via the Nx interface. The second communication device can then send the second message to the first communication device via the Xn interface. In this case, the second message indicates agreement to switch computing service from the first communication device to the second communication device, or it indicates disagreement to switch computing service from the first communication device to the second communication device.

[0153] Another possible scenario is that the first message requests the first and second communication devices to cooperate in providing computing services. The second communication device, based on its own communication status, computing resources, computing status, and the first message, determines whether it can cooperate with the first communication device to provide computing services to the terminal. As an example, and not a limitation, the CU / DU in the second communication device outputs the first message and related information (such as communication status) to the second SU via the Nx interface. The second SU, based on the communication status, computing resources, computing status, and the first message, determines whether it can cooperate with the first communication device to provide computing services to the terminal and feeds this back to the CU / DU in the second communication device via the Nx interface. The second communication device can then send a second message to the first communication device via the Xn interface. In this case, the second message indicates agreement to the first and second communication devices cooperating in providing computing services, or it indicates disagreement with the first and second communication devices cooperating in providing computing services.

[0154] In one possible implementation, when the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating to provide computing services, the second message indicates any of the following: computing service switching mode, reselection of target device, computing service provided by the terminal, or computing service provided by the terminal and the cloud server.

[0155] The second communication device can be considered as an example of a target device, and reselecting a target device can be understood as selecting a device other than the second communication device as the target device.

[0156] Furthermore, the provision of computing services by the terminal or by both the terminal and the cloud server is merely an example and should not constitute any limitation on this application. Exemplarily, the second message may instruct other rearrangement or redistribution methods, such as the terminal and base station collaboratively providing computing services, or the terminal, base station, and cloud server collaboratively providing computing services, etc.

[0157] The aforementioned computing service switching methods include, but are not limited to: synchronous switching, asynchronous switching, and collaborative processing.

[0158] Synchronous handover refers to a first communication device requesting a switch in communication services while simultaneously requesting a switch in computing services. For example, the first communication device may simultaneously send handover request 1 and handover request 2; or, handover request 1 and handover request 2 may be carried in the same signaling message; or, handover request 1 and handover request 2 may be transmitted on the same time-frequency resource. Here, "simultaneously" can be understood as the same point in time or within a certain time period; this application does not limit this. For example, sending handover request 1 and handover request 2 simultaneously can be understood as sending at the same point in time or within a certain time period. The aforementioned time period can be understood in context; for example, in this application, the aforementioned time period may be less than or equal to the time interval between sending handover request 1 and receiving the response to handover request 1.

[0159] In one possible implementation, the first message is sent before the fourth message is received. The fourth message responds to the third message, indicating agreement to switch the communication service from the first communication device to the second communication device, while the third message requests a switch from the first to the second communication device. In other words, the first communication device requests a switch to the computing service before the second communication device responds to the communication service switch request. Or, the request to switch the computing service is sent before the communication service switch is complete. This timely request to switch the computing service reduces the possibility of computing service interruption, thus ensuring a better user experience. The first and third messages can be carried in the same signaling or in different signaling.

[0160] Asynchronous switching can be understood as follows: when the first communication device determines that the device providing communication services to the terminal is switching from the first communication device to the second communication device, a first message is sent if preset conditions are met. These preset conditions include one or more of the following: completion of a historical calculation task; a first time interval remaining before the third message is sent; or the terminal triggers the first communication device to send the first message. It should be understood that the above preset conditions are merely examples and should not constitute any limitation on this application. For example, the preset conditions could also be determined / set by the application itself to request a switch of computing services.

[0161] When the first communication device sends a first message under preset conditions, it helps ensure load balancing for the second communication device. For example, if multiple first communication devices request to switch computing services to the same second communication device after determining that their communication services have switched from the first device to the same second device, the load on the second communication device will increase, potentially leading to its failure. By requesting to switch computing services only when the preset conditions are met, it helps avoid multiple first communication devices simultaneously switching their computing services to the same second communication device, thus ensuring load balancing for the second communication device. Secondly, it helps ensure the timeliness of computing tasks and data privacy. For example, if the first communication device completes a historical computing task before switching, it can ensure that the historical computing task is processed promptly without being transmitted to the second communication device, thus helping to protect data privacy. Thirdly, it helps ensure the accuracy of computing tasks. For example, in scenarios where the model deployed on the first communication device has better performance, requesting to switch only after the preset conditions are met can improve the accuracy of the current computing task.

[0162] In one example, a first communication device sends a third message to request a switch of communication service from the first communication device to a second communication device. After a first duration has elapsed since the third message was sent, the first communication device sends a first message to request a switch of computing service from the first communication device to the second communication device. The first duration can be predefined.

[0163] In another example, the first communication device sends a third message to request a switch of communication service from the first communication device to the second communication device. After the first communication device completes its historical calculation task, it sends a first message to request a switch of calculation service from the first communication device to the second communication device. The first duration can be predefined.

[0164] In another example, a first communication device sends a third message to request a switch of communication service from the first communication device to a second communication device. The first communication device receives a trigger message from a terminal to trigger the first communication device to send a first message, which in turn sends a first message to request a switch of computing service from the first communication device to the second communication device.

[0165] In one possible implementation, the method 400 further includes: the second communication device sending a seventh message to the core network device, the seventh message indicating a modification to the forwarding path of the data flow. As an example, and not a limitation, after the computing service is switched from the first communication device to the second communication device, the second communication device sends the seventh message to the core network device to indicate a modification to the forwarding path of the data flow.

[0166] In other words, after the computing service is switched from the first communication device to the second communication device, the second communication device can instruct the core network equipment to modify the forwarding path of the data stream. This allows the core network equipment to determine the forwarding path of the downlink computing data based on the aforementioned seventh message, thus improving system reliability.

[0167] For example, the second communication device sends a path switching request to the core network device. The path switching request may carry an indication to modify the forwarding path of the data stream so that the core network device can forward data based on the changed forwarding path.

[0168] In one possible implementation, in the case of asynchronous switching, the third message indicates the switching time of the computing service; for example, this switching time could be the time when the first message was sent. By including the switching time of the computing service in the request to switch communication services, the second communication device can reserve computing resources for it, ensuring that the computing service can also switch to the second communication device, thus improving the continuity of the computing service.

[0169] In one possible implementation, in the case of asynchronous switching, before the first communication device sends the first message, the method 400 further includes: the first communication device sending a fifth message, and correspondingly, the second communication device receiving the fifth message, the fifth message indicating the forwarding settings of the computing task, the forwarding settings including one or more of the following: a forwarding path, the address of each node on the forwarding path or the identifier of the data stream, the forwarding path including the first communication device and the second communication device.

[0170] In other words, in a scenario where the second communication device provides communication services and the first communication device provides computing services (i.e., the device providing communication services is switched from the first communication device to the second communication device, but the device providing computing services is still the first communication device), the first communication device can instruct the forwarding settings of the computing task. The forwarding path in the forwarding settings includes the first communication device and the second communication device. In other words, the first communication device performs a computing task, and its computing result needs to be forwarded to the terminal by the second communication device. Alternatively, the uplink computing data of the terminal needs to be forwarded to the first communication device by the second communication device, and the first communication device performs the computing task.

[0171] For example, before the first communication device sends the first message, the first communication device sends a fifth message, which indicates that for downlink data, the forwarding path is core network equipment, the first communication device (specifically, the CU / DU in the first communication device), the SU (first SU) in the first communication device, the second communication device (specifically, the CU / DU in the second communication device), and the terminal. The fifth message also indicates which data streams are forwarded according to the forwarding path, and may also refer to the addresses of each node, such as the port numbers of each node.

[0172] It is understandable that the fifth message may also indicate QoS requirements for computing services between nodes, execution progress of computing tasks, etc.

[0173] In one possible implementation, before the second communication device receives the first message, the method 400 further includes: the second communication device sending a sixth message to the core network device, the sixth message indicating one or more of the following: a forwarding path, the address of each node on the forwarding path, the identifier of the data flow, or indication information indicating that the task session identifier and / or the QoS flow identifier corresponding to the computing service remain unchanged.

[0174] The second communication device instructs the core network equipment on the above content, so that when the core network equipment sends downlink computing data, it can send it based on the above content, avoiding the core network equipment from mistakenly thinking that the computing service has also switched to the second communication device, thus improving the reliability of the system.

[0175] For example, the second communication device sends a path switching request to the core network equipment, the path switching request indicating one or more of the following: forwarding path, addresses of each node on the forwarding path, identifiers of data streams, or indication information.

[0176] In one possible implementation, before the second communication device receives the first message, the method 400 further includes: sending context information indicating one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, computing data, or the execution log of the computing task.

[0177] By leveraging contextual information, the first and second communication devices can collaborate more effectively, reducing redundant work and improving execution efficiency. For example, the application, model, or function corresponding to the computing service can enable the second communication device to determine which application, model, or function needs to be migrated. The first communication device instructs on computational data, which can be raw input data, intermediate output data, or other auxiliary data, etc. This application does not limit this; instructing on computational data helps improve computational efficiency. The execution log of the computing task helps the second communication device track the execution status, progress, and historical records of the computing task, thus contributing to improved execution efficiency.

[0178] The aforementioned context information can be carried in the handover request, such as a handover request for computing services or a handover request for communication services; it can also be carried in the data forwarding after the handover, and this application does not limit this.

[0179] In one possible implementation, the first communication device may send a first indication message to the terminal, indicating the device providing computing services to the terminal and / or the computing service switching mode. This computing service switching mode refers to the switching mode of the device providing computing services to the terminal when the device providing communication services to the terminal switches from the first communication device to the second communication device. Accordingly, the terminal receives the aforementioned first indication message. The computing service switching mode may, for example, be the synchronous switching, asynchronous switching, or cooperative processing described above.

[0180] As an example and not a limitation, the aforementioned first indication information can be carried in an RRC configuration message (as shown in step 104 of Figure 1). For example, in a synchronous handover scenario, the source base station sends an RRC configuration message, which may indicate that the handover mode for computing services is synchronous handover, and the device providing computing services to the terminal is switched from the source base station (specifically, it may be a SU in the source base station) to the target base station (specifically, it may be a SU in the target base station).

[0181] In one possible implementation, the terminal sends first information to the first communication device, the first information indicating the supported computing service switching mode and / or computing resource requirements.

[0182] By way of example and not limitation, before the first communication device sends the first message, the terminal sends first information to the first communication device, which indicates the supported computing service switching mode and / or computing resource requirements. For example, the terminal may indicate the aforementioned first information during the reporting of the measurement results of the reference signal. In this way, the first communication device can determine the computing service switching mode and / or computing resource requirements based on the aforementioned first information. For example, if the terminal supports synchronous switching, the SU in the first communication device can determine that the computing service switching mode is synchronous switching. As another example, the SU in the first communication device can determine the computing resource requirements requested from the second communication device based on the computing resource requirements reported by the terminal, and carry them in the first message. It is understood that the computing resource requirements reported by the terminal and the computing resource requirements requested by the first communication device may be the same or different, and this application does not limit this.

[0183] The detailed processes of synchronous switching, asynchronous switching, and collaborative processing will be described below with reference to Figures 5 to 7. It should be understood that in the embodiments shown in Figures 5 to 7, the first communication device is exemplified by a source access network device, and the second communication device is exemplified by a target access network device. The computing task is exemplified by an AI task. However, this should not constitute any limitation on the embodiments of this application. For example, the computing task can also be other types of computing tasks, and the first and second communication devices can also be other types of devices.

[0184] Figure 5 is a detailed flowchart of the communication method provided in the embodiments of this application.

[0185] In step 501, the measurement and selection of the target base station are performed.

[0186] As an example and not a limitation, the terminal may measure reference signals transmitted by the source access network device and / or adjacent access network devices, and report the measurement results to the source access network device. Based on the measurement results, the source access network device may determine the device to switch to providing communication services and determine the target access network device; that is, it determines that the device providing communication services to the terminal will be switched from the source access network device to the target access network device. The specific process of measuring and selecting the target access network device can be found in existing technologies and will not be elaborated here.

[0187] In step 502, the source access network device obtains the AI ​​task instruction.

[0188] For example, the communication unit (denoted as the source communication unit) in the source access network device instructs the SU (denoted as the source SU) in the source access network device that the communication service is about to be switched from the source access network device to the target access network device. The source SU determines that the computing service switching method is synchronous switching. For an understanding of synchronous switching, please refer to the above. The source SU instructs the source communication unit to switch the computing service in a synchronous manner and instructs the source communication unit to provide one or more of the following: the identifier of the application corresponding to the computing service, the identifier of the model corresponding to the computing service, the identifier of the function corresponding to the computing service, the execution progress of the AI ​​task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the AI ​​task, or the execution logic of the AI ​​task. The source communication unit and the source SU can interact through the Nx interface. The source communication unit can be a CU / DU, which can be separate or not, and this application does not limit this. It should be understood that the above example is a case where the source communication unit and the source SU are separate, but this should not constitute any limitation on this application. The source communication unit and the source SU can also be not separate, and this application does not limit this.

[0189] In step 503, the source access network device sends handover request 1 and handover request 2. The target access network device receives handover request 1 and handover request 2.

[0190] The handover request 1 is used to request the device providing communication services to the terminal to switch from the source access network device to the target access network device, and the handover request 2 is used to request the device providing computing services to the terminal to switch from the source access network device to the target access network device. The handover request 1 and handover request 2 can be carried in the same signaling or in different signaling, and this application does not limit this.

[0191] The aforementioned switch request 2 may indicate one or more of the following: the application corresponding to the aforementioned computing service, the model corresponding to the aforementioned computing service, the function corresponding to the aforementioned computing service, the execution progress of the AI ​​task, computing resource requirements, QoS requirement information corresponding to the computing service, orchestration information of the AI ​​task, or the execution logic of the AI ​​task. For an understanding of the above parameters, please refer to the explanation in Figure 4, which will not be repeated here.

[0192] In step 504, the target access network device obtains the evaluation results.

[0193] After receiving handover request 2, the target access network device determines whether it can provide computing services to the terminal based on its own communication status, computing resource status, computing status, and handover request 2, and obtains the evaluation result. As an example, and not a limitation, the communication unit (denoted as the target communication unit) in the target access network device outputs handover request 2 and related information (such as communication status) to the SU (denoted as the target SU) in the target access network device through the Nx interface. The target SU, based on the communication status, computing resource status, computing status, and handover request 2, determines whether it can provide computing services to the terminal and feeds back the evaluation result to the target communication unit through the Nx interface. The evaluation result may, for example, agree to the handover of computing services from the source access network device to the target access network device (specifically, from the source SU to the target SU), or disagree to the handover of computing services from the source access network device to the target access network device. The target communication unit can be a CU / DU, which can be separate or not; this application does not limit this. It should be understood that the above example illustrates the case where the target communication unit and the target SU are separated, but this should not constitute any limitation on this application. The target communication unit and the target SU may also be inseparable, and this application does not limit this.

[0194] In step 505, the target access network device sends handover response 1 and handover response 2. The source access network device receives handover response 1 and handover response 2.

[0195] The handover response 1 is in response to handover request 1, and the handover response 2 is in response to handover request 2. The handover response 1 and handover response 2 may be carried in the same signaling or in different signaling, and this application does not limit this.

[0196] The aforementioned handover response 1 can indicate consent to the handover of communication services from the source access network device to the target access network device, or disagreement with the handover of communication services from the source access network device to the target access network device; the aforementioned handover response 2 can indicate consent to the handover of computing services from the source access network device to the target access network device, or disagreement with the handover of computing services from the source access network device to the target access network device. For details regarding the specific content carried in handover response 2, please refer to the explanation of the content carried in the second message, which will not be elaborated here.

[0197] In step 506, the source access network device sends context information. Correspondingly, the target access network device receives the context information.

[0198] For an explanation of the contextual information, please refer to the explanation in Figure 4, which will not be elaborated here.

[0199] In step 507, the communication service is switched and the computing service is switched.

[0200] Communication services are switched from the source access network device to the target access network device, and computing services are switched from the source access network device to the target access network device.

[0201] As an example, and not a limitation, the communication service is switched from the source access network device to the target access network device. Specifically, this includes: the source access network device sending an RRC configuration message to the terminal, and the terminal receiving the aforementioned RRC configuration message. Further, the terminal executes the RACH procedure. For a more detailed explanation, please refer to steps 104 and 105 in Figure 1, which will not be repeated here.

[0202] As an example, and not a limitation, the switching of computing services from the source access network device to the target access network device can specifically include: the target access network device invoking and configuring the application / model / function based on the application / model / function corresponding to the computing service and the QoS requirement information corresponding to the computing service; the target access network device executing the computing task based on context information; and the source access network device stopping the computing task process.

[0203] For example, the computing service is switched from the source access network device to the target access network device. Specifically, this can be a switch from the source unit (SU) to the target unit (SU). Taking the migration of the model's computing service as an example, the process of switching the computing service from the source unit to the target unit can specifically include: the target unit, based on the model indication (such as the model identifier) ​​and the QoS requirement information corresponding to the computing service (such as the requirements for parameters such as accuracy / latency), calls and configures the local model (configuration includes model quantization / pruning settings, intermediate data compression settings, etc.), or the source unit sends the model to the target unit. Further, the target unit starts executing the computing task according to the context information, while the source unit stops the computing task process.

[0204] In step 508, the target access network device sends a path switching request, which carries a path modification indication for the AI ​​data stream. The core network device receives the path switching request.

[0205] For example, the target access network device sends a path switching request to the core network device. This request may include an indication to modify the forwarding path of the AI ​​data stream, so that the core network device can forward data based on the modified forwarding path. For instance, taking downlink data as an example, the modified forwarding path could be that the application's cloud server sends downlink data to the core network device, the core network device sends the downlink data to the target access network device via the NG interface, the target communication unit in the target access network device outputs the downlink data to the target SU, the target SU executes the AI ​​task, and sends the calculation result to the terminal through the target access network device.

[0206] In the above scheme, when the device providing communication services to the terminal is switched from the source access network device to the target access network device, the source access network device can request to switch the computing service to the target access network device as well (specifically, it can be the target SU in the target access network device). In this way, in the event of a communication service switch, timely requesting to switch the computing service helps to reduce the possibility of computing service interruption, thereby ensuring user experience.

[0207] Figure 6 is another detailed flowchart of the communication method provided in the embodiments of this application.

[0208] In step 601, the selection of the target access network device is measured.

[0209] As an example and not a limitation, the terminal may measure reference signals transmitted by the source access network device and / or adjacent access network devices, and report the measurement results to the source access network device. Based on the measurement results, the source access network device may determine the device to switch to providing communication services and determine the target access network device; that is, it determines that the device providing communication services to the terminal will be switched from the source access network device to the target access network device. The specific process of measuring and selecting the target access network device can be found in existing technologies and will not be elaborated here.

[0210] In step 602, the source access network device obtains the AI ​​task instruction.

[0211] For example, the communication unit (source communication unit) in the source access network device indicates that the communication service of the SU (source SU) in the source access network device is about to be switched from the source access network device to the target access network device. The source SU determines that the computing service switching method is asynchronous switching. For an understanding of asynchronous switching, please refer to the above. The source SU instructs the source communication unit to switch the computing service asynchronously and instructs the source communication unit to provide one or more of the following: the identifier of the application corresponding to the computing service, the identifier of the model corresponding to the computing service, the identifier of the function corresponding to the computing service, the execution progress of the AI ​​task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the AI ​​task, or the execution logic of the AI ​​task. The source communication unit and the source SU can interact through the Nx interface. For an explanation of the source communication unit and the source SU, please refer to Figure 5, which will not be repeated here.

[0212] In step 603, the terminal performs a switch of communication services.

[0213] As an example, and not a limitation, the switching of communication services by a terminal includes the following steps:

[0214] Step 1: The source access network device sends a handover request 1 to the target access network device. This handover request 1 requests that the device providing communication services to the terminal be switched from the source access network device to the target access network device. Accordingly, the target access network device receives the handover request 1. In one possible design, the handover request 1 carries the handover time for computing services.

[0215] Step 2: The target access network device sends a handover response 1, and the source access network device receives the handover response 1 accordingly. This handover response 1 indicates that the target access network device agrees to the handover of communication services from the source access network device to the target access network device.

[0216] Step 3: The communication service is switched from the source access network device to the target access network device. As an example, and not a limitation, this switch includes: the source access network device sending an RRC configuration message to the terminal, and the terminal receiving the RRC configuration message. Further, the terminal executes the RACH procedure. For a more detailed explanation, please refer to steps 104 and 105 in Figure 1, which will not be repeated here.

[0217] In one possible implementation, the source access network device may also indicate the forwarding settings of the AI ​​task to the target access network device. The forwarding settings include one or more of the following: forwarding path, addresses of nodes on the forwarding path, or identifiers of data streams, wherein the forwarding path includes both the source access network device and the target access network device.

[0218] In other words, before sending handover request 2, the source access network device can indicate the forwarding settings of the AI ​​task to the target access network device. The forwarding path in the forwarding settings includes both the source access network device and the target access network device. In other words, the source access network device (specifically, the source SU) performs the AI ​​task, and its calculation result needs to be forwarded to the terminal by the target access network device. Alternatively, the uplink calculation data of the terminal needs to be forwarded to the source access network device by the target access network device, and the source access network device performs the AI ​​task.

[0219] When a target access network device sends a path switching request to a core network device, it may carry the forwarding path, the addresses of each node on the forwarding path, the identifier of the data flow, or indication information. This indication information indicates that the task session identifier and / or the QoS flow identifier corresponding to the computing service remain unchanged.

[0220] In step 604, the source access network device sends a handover request 2, and the target access network device receives the handover request 2 accordingly.

[0221] Under certain preset conditions, the source access network device sends a handover request 2, which requests the computing service to be switched from the source access network device to the target access network device. These preset conditions include one or more of the following: completion of a historical AI task; a first time interval remaining since sending handover request 1; or the terminal triggering the source access network device to send handover request 2.

[0222] It is understood that the handover request 2 can be sent after the communication service handover is completed or before the communication service handover is completed. This application does not limit this, as long as the preset conditions are met, the handover request 2 can be sent.

[0223] In step 605, the target access network device obtains the evaluation results.

[0224] After receiving handover request 2, the target access network device determines whether it can provide computing services to the terminal based on its own communication status, computing resource status, computing status, and handover request 2, and obtains the evaluation result. As an example, and not a limitation, the communication unit (target communication unit) in the target access network device outputs handover request 2 and related information (such as communication status) to the SU (target SU) in the target access network device through the Nx interface. The target SU, based on the communication status, computing resource status, computing status, and handover request 2, determines whether it can provide computing services to the terminal and feeds back the evaluation result to the target communication unit through the Nx interface. The evaluation result may, for example, agree to the handover of computing services from the source access network device to the target access network device, or disagree to the handover of computing services from the source access network device to the target access network device. For an explanation of the target communication unit and the target SU, please refer to Figure 5, which will not be repeated here.

[0225] In step 606, the target access network device sends a handover response 2. The source access network device receives the handover response 2.

[0226] This handover response 2 is in response to handover request 2. The aforementioned handover response 2 may indicate agreement to the handover of computing services from the source access network device to the target access network device, or disagreement to the handover of computing services from the source access network device to the target access network device. For details regarding the specific content carried in handover response 2, please refer to the explanation of the content carried in the second message; it will not be elaborated upon here.

[0227] In step 607, the source access network device sends context information. Correspondingly, the target access network device receives the context information.

[0228] For an explanation of the contextual information, please refer to the explanation in Figure 4, which will not be elaborated here.

[0229] In step 608, the computing service is switched.

[0230] As an example, and not a limitation, the switching of computing services from the source access network device to the target access network device can specifically include: the target access network device invoking and configuring the application / model / function based on the application / model / function corresponding to the computing service and the QoS requirement information corresponding to the computing service; the target access network device executing the computing task based on context information; and the source access network device stopping the computing task process.

[0231] For example, the computing service is switched from the source access network device to the target access network device. Specifically, this can be a switch from the source unit (SU) to the target unit (SU). Taking the migration of the model's computing service as an example, the process of switching the computing service from the source unit to the target unit can specifically include: the target unit, based on the model indication (such as the model identifier) ​​and the QoS requirement information corresponding to the computing service (such as the requirements for parameters such as accuracy / latency), calls and configures the local model (configuration includes model quantization / pruning settings, intermediate data compression settings, etc.), or the source unit sends the model to the target unit. Further, the target unit starts executing the computing task according to the context information, while the source unit stops the computing task process.

[0232] In step 609, the target access network device sends a computing service migration configuration to the core network device, and the core network device receives the computing service migration configuration.

[0233] For example, the target access network device sends a computing service migration configuration to the core network device to indicate an updated forwarding path for the AI ​​data stream, so that the core network device can forward data based on the updated forwarding path. For instance, taking downlink data as an example, the updated forwarding path could be that the application's cloud server sends downlink data to the core network device, the core network device sends this downlink data to the target access network device via the NG interface, the target communication unit in the target access network device outputs the downlink data to the target SU, the target SU executes the AI ​​task, and feeds back the calculation result to the target communication unit. The target access network device then sends the calculation result to the terminal. In one possible implementation, the computing service migration configuration can also indicate the QoS requirement information corresponding to the updated computing service.

[0234] In the above scheme, the source access network device sends a handover request 2 when preset conditions are met. This helps ensure load balancing of the target access network device. For example, if multiple source access network devices request to switch their computing services to a target access network device after determining that their communication services have switched to that device, the load on that target access network device will increase rapidly, potentially leading to its failure. By requesting to switch computing services only when preset conditions are met, it avoids the simultaneous switching of computing services from multiple source access network devices to the same target access network device, thus ensuring load balancing. Secondly, it helps ensure the timeliness of AI tasks and data privacy. For instance, if the source access network device completes a historical AI task before switching, it ensures that the historical AI task is processed promptly without being transmitted to the target access network device, thus protecting data privacy. Thirdly, it helps ensure the accuracy of AI tasks. For example, in scenarios where the model deployed on the source access network device has better performance, requesting a switch only when preset conditions are met can improve the accuracy of the current AI task.

[0235] Figure 7 is another detailed flowchart of the communication method provided in the embodiments of this application.

[0236] In step 701, the selection of the target access network device is measured.

[0237] As an example and not a limitation, the terminal may measure reference signals transmitted by the source access network device and / or adjacent access network devices, and report the measurement results to the source access network device. Based on the measurement results, the source access network device may determine the device to switch to providing communication services and determine the target access network device; that is, it determines that the device providing communication services to the terminal will be switched from the source access network device to the target access network device. The specific process of measuring and selecting the target access network device can be found in existing technologies and will not be elaborated here.

[0238] In step 702, the source access network device obtains the AI ​​task instruction.

[0239] For example, the communication unit (source communication unit) in the source access network device indicates that the communication service of the SU (source SU) in the source access network device is about to be switched from the source access network device to the target access network device. The source SU determines that the computing service switching mode is collaborative processing. For an understanding of collaborative processing, please refer to the above. The source SU instructs the source communication unit to switch the computing service to collaborative processing and instructs the source communication unit to provide one or more of the following: the identifier of the application corresponding to the computing service, the identifier of the model corresponding to the computing service, the identifier of the function corresponding to the computing service, the collaborative processing mode, the execution progress of the computing task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the AI ​​task, or the execution logic of the AI ​​task. The source communication unit and the source SU can interact through the Nx interface. For an explanation of the source communication unit and the source SU, please refer to the explanation in Figure 5, which will not be repeated here.

[0240] In one possible implementation, the above-mentioned collaborative processing methods include one or more of the following: federated learning, data augmentation, model output fusion, and model splitting for training or inference. For an understanding of these collaborative processing methods, please refer to the explanation in Figure 4; further details will not be provided here.

[0241] In step 703, the source access network device sends handover request 1 and handover request 2. The target access network device receives handover request 1 and handover request 2.

[0242] The handover request 1 is used to request the device providing communication services to the terminal to switch from the source access network device to the target access network device. The handover request 2 is used to request the source access network device and the target access network device to cooperate in providing computing services. The handover request 1 and handover request 2 can be carried in the same signaling or in different signaling, and this application does not limit this.

[0243] The aforementioned switch request 2 may indicate one or more of the following: the application corresponding to the aforementioned computing service, the model corresponding to the aforementioned computing service, the function corresponding to the aforementioned computing service, the collaborative processing method, the execution progress of the AI ​​task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the AI ​​task, or the execution logic of the AI ​​task. For an understanding of the above parameters, please refer to the explanation in Figure 4, which will not be repeated here.

[0244] In step 704, the target access network device obtains the evaluation results.

[0245] After receiving handover request 2, the target access network device determines whether it can collaborate with the source access network device to provide computing services to the terminal based on its own communication status, computing resources, computing status, and handover request 2, and obtains an evaluation result. As an example, and not a limitation, the communication unit (target communication unit) in the target access network device outputs handover request 2 and related information (such as communication status) to the SU (target SU) in the target access network device via the Nx interface. The target SU, based on its communication status, computing resources, computing status, and handover request 2, determines whether it can collaborate with the source access network device (specifically, the source SU) to provide computing services to the terminal, and feeds back the evaluation result to the target communication unit via the Nx interface. The evaluation result may, for example, agree that the source and target access network devices can collaborate to provide computing services, or disagree that they can collaborate.

[0246] In step 705, the target access network device sends handover response 1 and handover response 2. The source access network device receives handover response 1 and handover response 2.

[0247] The handover response 1 is in response to handover request 1, and the handover response 2 is in response to handover request 2. The handover response 1 and handover response 2 may be carried in the same signaling or in different signaling, and this application does not limit this.

[0248] The aforementioned handover response 1 can indicate agreement to handover the communication service from the source access network device to the target access network device, or disagreement to handover the communication service from the source access network device to the target access network device; the aforementioned handover response 2 can indicate agreement to the source access network device and the target access network device jointly providing computing services, or disagreement to the source access network device and the target access network device jointly providing computing services. For details regarding the specific content carried in handover response 2, please refer to the explanation of the content carried in the second message, which will not be elaborated here.

[0249] In step 706, the source access network device sends context information. Correspondingly, the target access network device receives the context information.

[0250] For an explanation of the contextual information, please refer to the explanation in Figure 4, which will not be elaborated here.

[0251] In step 707, the communication service is switched and the source access network device and the target access network device cooperate to provide computing services.

[0252] As an example, and not a limitation, the communication service is switched from the source access network device to the target access network device. Specifically, this includes: the source access network device sending an RRC configuration message to the terminal, and the terminal receiving the aforementioned RRC configuration message. Further, the terminal executes the RACH procedure. For a more detailed explanation, please refer to steps 104 and 105 in Figure 1, which will not be repeated here.

[0253] As an example, and not a limitation, the source access network device and the target access network device collaboratively provide computing services. Specifically, this may include: the target access network device invoking and configuring the application / model / function based on the application / model / function corresponding to the computing service and the QoS requirement information corresponding to the computing service; and the target access network device collaborating with the source access network device to execute computing tasks based on context information and collaborative processing methods.

[0254] For example, the source access network device and the target access network device collaboratively provide computing services. Specifically, this can be achieved by the source SU and the target SU collaboratively providing computing services. Taking the migration of model computing services as an example, the collaborative provision of computing services by the source SU and the target SU can specifically include: the target SU calling and configuring a local model (configuration including model quantization / pruning settings, intermediate data compression settings, etc.) based on the model instructions (such as model identifier) ​​and the QoS requirement information corresponding to the computing service (such as requirements for parameters such as accuracy / latency) from the source SU, or the source SU sending the model to the target SU. Further, the target SU, based on context information and the collaborative processing method, collaboratively executes computing tasks with the source SU.

[0255] In step 708, the target access network device sends a path switching request to the core network device, the path switching request carrying the cooperative processing configuration. The core network device receives the path switching request.

[0256] For example, the target access network device sends a path switching request to the core network device. The path switching request may carry a collaborative processing configuration, which may include one or more of the following: the forwarding path of the AI ​​data stream, the addresses of each node on the forwarding path, or QoS requirement information corresponding to the computing service.

[0257] In step 709, the computing service is switched.

[0258] It is understandable that the entire computing service can be migrated in the future. If the preset conditions are met, the computing service will be switched from the source access network device to the target access network device. The preset conditions include one or more of the following: completion of the historical AI task; the time elapsed since the sending of the switch request 1 reaches a first duration; and the terminal triggers the switching of the computing service from the source access network device to the target access network device.

[0259] In the above scheme, by instructing collaborative processing methods, the advantages of distributed computing can be fully utilized to improve computing efficiency, overall system performance, and reliability. For example, it can fully leverage different personalized models and data on different devices, enabling smooth switching of computing services and avoiding inconsistent service experiences caused by large differences in models / data after switching, such as in video generation tasks. Furthermore, different collaborative processing methods can also help balance the load.

[0260] The methods provided in the embodiments of this application have been described in detail above with reference to the accompanying drawings. The apparatus provided in the embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0261] It should be understood that the devices shown in Figures 8 and 9 can be used to implement the functions of the first communication device or the second communication device in the above method embodiments, and thus can also achieve the beneficial effects of the above method embodiments.

[0262] Figure 8 is a schematic block diagram of a communication device 800 provided in an embodiment of this application.

[0263] As shown in Figure 8, the communication device 800 includes a processing module 810 and a transceiver module 820. The communication device 800 can be used to implement the functions of the first or second communication device in any of the method embodiments shown in Figures 4 to 7.

[0264] The modules included in the communication device 800 can be implemented through software and / or hardware.

[0265] One possible implementation is that the communication device 800 can be used to implement the steps performed by the first communication device in any of the method embodiments shown in Figures 4 to 7. The first communication device can be an access network device, a component in the access network device (e.g., a chip, a chip system, or a processor), or a device that can be used in conjunction with the access network device, or a logic module or software that can implement all or part of the functions of the access network device.

[0266] Another possible implementation is that the communication device 800 can be used to implement the steps performed by the second communication device in any of the method embodiments shown in Figures 4 to 7. The second communication device can be an access network device, a component in the access network device (e.g., a chip, a chip system, or a processor), or a device that can be used in conjunction with the access network device, or a logic module or software that can implement all or part of the functions of the access network device.

[0267] For example, the communication device 800 may include modules or units that correspond one-to-one with the methods / operations / steps / actions described in the method embodiments shown in Figures 4 to 7. The modules or units may be hardware circuits, software, or a combination of hardware circuits and software.

[0268] For example, when the communication device 800 is used to implement the function of the first communication device in the method embodiment shown in FIG4, the processing module 810 is used to determine that the device providing communication services to the terminal is switched from the first communication device to the second communication device; the transceiver module 820 is used to send a first message, which requests that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requests that the first communication device and the second communication device cooperate to provide computing services.

[0269] In one possible implementation, the first message indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

[0270] In one possible implementation, the first message also indicates the collaborative processing method.

[0271] In one possible implementation, the above-mentioned collaborative processing methods include one or more of the following: federated learning, data augmentation, model output fusion, model splitting for training or inference.

[0272] In one possible implementation, the transceiver module 820 is further configured to receive a second message. When the first message requests that the computing service be switched from the first communication device to the second communication device, the second message indicates agreement to switch the computing service from the first communication device to the second communication device, or the second message indicates disagreement to switch the computing service from the first communication device to the second communication device; or, when the first message requests that the first communication device and the second communication device cooperate in providing computing services, the second message indicates agreement to cooperate in providing computing services from the first communication device and the second communication device, or the second message indicates disagreement to cooperate in providing computing services from the first communication device and the second communication device.

[0273] In one possible implementation, when the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating to provide computing services, the second message indicates any of the following: computing service switching mode, reselection of target device, computing service provided by the terminal, or computing service provided by the terminal and the cloud server.

[0274] In one possible implementation, the transceiver module 820 is further configured to send context information indicating one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, computing data, or the execution log of the computing task.

[0275] In one possible implementation, the transceiver module 820 is further configured to send a third message requesting a switch of communication service from the first communication device to the second communication device; and receive a fourth message indicating agreement to switch communication service from the first communication device to the second communication device.

[0276] In one possible implementation, the aforementioned third message indicates the switching time for the computing service.

[0277] In one possible implementation, the transceiver module 820 is specifically used to: send a first message when a preset condition is met, the preset condition including one or more of the following: completing a historical calculation task; the time elapsed since the third message was sent has reached a first duration; and the terminal triggers the first communication device to send the first message.

[0278] In one possible implementation, the transceiver module 820 is further configured to send a fifth message indicating the forwarding settings of the computing task. The forwarding settings include one or more of the following: a forwarding path, the address of each node on the forwarding path, or the identifier of the data stream. The forwarding path includes a first communication device and a second communication device.

[0279] In one possible implementation, the first message is sent before the fourth message is received.

[0280] For example, when the communication device 800 is used to implement the function of the second communication device in the method embodiment shown in FIG4, the transceiver module 820 is used to receive a first message. The first message requests that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requests that the first communication device and the second communication device cooperate to provide computing services. The first communication device is the device that provides communication services to the terminal before the communication service switch, and the second communication device is the device that provides communication services to the terminal after the communication service switch.

[0281] In one possible implementation, the first message indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the QoS requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

[0282] In one possible implementation, the first message also indicates the collaborative processing method.

[0283] In one possible implementation, the above-mentioned collaborative processing methods include one or more of the following: federated learning, data augmentation, model output fusion, model splitting for training or inference.

[0284] In one possible implementation, the transceiver module 820 is further configured to send a second message: when the first message requests the computing service to be switched from the first communication device to the second communication device, the second message indicates agreement to switch the computing service from the first communication device to the second communication device, or the second message indicates disagreement to switch the computing service from the first communication device to the second communication device; or, when the first message requests the first communication device and the second communication device to cooperate in providing computing services, the second message indicates agreement to cooperate in providing computing services from the first communication device and the second communication device, or the second message indicates disagreement to cooperate in providing computing services from the first communication device and the second communication device.

[0285] In one possible implementation, when the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating to provide computing services, the second message indicates any of the following: computing service switching mode, reselection of target device, computing service provided by the terminal, or computing service provided by the terminal and the cloud server.

[0286] In one possible implementation, the transceiver module 820 is further configured to receive context information indicating one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, computing data, or the execution log of the computing task.

[0287] In one possible implementation, the transceiver module 820 is further configured to receive a third message requesting a switch of communication service from the first communication device to the second communication device; and send a fourth message indicating agreement to switch communication service from the first communication device to the second communication device.

[0288] In one possible implementation, the aforementioned third message indicates the switching time for the computing service.

[0289] In one possible implementation, the transceiver module 820 is further configured to receive a fifth message indicating the forwarding settings of the computing task. The forwarding settings include one or more of the following: a forwarding path, the address of each node on the forwarding path, or the identifier of the data stream. The forwarding path includes a first communication device and a second communication device.

[0290] In one possible implementation, the transceiver module 820 is further configured to send a sixth message to the core network device, the sixth message indicating one or more of the following: forwarding path, addresses of each node on the forwarding path, identifier of the data flow, or indication information, the indication information indicating that the task session identifier and / or the QoS flow identifier corresponding to the computing service remain unchanged.

[0291] In one possible implementation, the first message is received before the fourth message is sent.

[0292] In one possible implementation, the transceiver module 820 is also used to send a seventh message to the core network device, which indicates a modification to the forwarding path of the data stream.

[0293] For a more detailed description of each of the above modules, please refer directly to the relevant descriptions in the method embodiment shown in Figure 4, which will not be repeated here.

[0294] It should be understood that the module division in the embodiments of this application is illustrative and only represents a logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional modules in the various embodiments of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0295] Figure 9 is another schematic block diagram of the communication device 900 provided in an embodiment of this application.

[0296] The communication device 900 can be a chip system, or an apparatus configured with a chip system to implement the methods described in the above-described method embodiments. In the embodiments of this application, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0297] As shown in FIG9, the communication device 900 may include a processor 910, which can be used to execute computer programs or instructions in memory to implement the steps performed by the first communication device or the second communication device in any of the embodiments shown in FIG4 to FIG7.

[0298] In one possible implementation, the communication device 900 further includes a communication interface 920. The communication interface 920 can be used to communicate with other devices via a transmission medium, thereby enabling the communication device 900 to communicate with other devices. The communication interface 920 can be, for example, a transceiver, interface, pin, bus, circuit, or a device capable of transmitting and receiving functions. The processor 910 can use the communication interface 920 to input and output data and to implement the steps performed by the first or second communication device in any of the embodiments shown in Figures 4 to 7.

[0299] In one possible implementation, the communication device 900 further includes at least one memory 930 for storing program instructions and / or data. The memory 930 is coupled to the processor 910. The coupling in this embodiment is an indirect coupling or communication connection between devices, units, or modules, and can be electrical, mechanical, or other forms, for information exchange between devices, units, or modules. The processor 910 may operate in conjunction with the memory 930. The processor 910 may execute program instructions stored in the memory 930. At least one of the at least one memory may be included in the processor.

[0300] It should be understood that the coupling in the embodiments of this application is an indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information interaction between devices, units, or modules. The processor 910 may operate in conjunction with the memory 930. The specific connection medium between the processor 910, communication interface 920, and memory 930 is not limited in the embodiments of this application. Optionally, the processor 910, communication interface 920, and memory 930 are connected via a bus 940. The bus 940 is represented by a thick line in Figure 9. The connection methods between other components are only illustrative and not intended to be limiting. The bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used in Figure 9, but this does not indicate that there is only one bus or one type of bus.

[0301] In one possible implementation, the communication device 900 is a system-on-a-chip (SoC). Alternatively, the processor 910 is an SoC.

[0302] This application also provides a communication system comprising a first communication device and a second communication device as described above. In one possible implementation, the first communication device may, for example, implement the steps performed by the first communication device in the method shown in FIG4, and the second communication device may, for example, implement the steps performed by the second communication device in the method shown in FIG4.

[0303] This application also provides a computer program product, which includes a computer program (also referred to as code or instructions) that, when run, can implement the steps executed by the first communication device or the second communication device in any of the embodiments shown in Figures 4 to 7.

[0304] This application also provides a computer-readable storage medium storing a computer program (also referred to as code or instructions). When the computer program is run, it can implement the steps performed by the first or second communication device in any of the embodiments shown in Figures 4 to 7.

[0305] It should be understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a microprocessor unit (MPU), a microcontroller unit (MCU), a graphics processing unit (GPU), an artificial intelligence processor (AI processor) or a neural processing unit (NPU), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or a combination of one or more discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0306] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be a cache, random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0307] The terms "unit," "module," etc., used in this specification can be used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. In the embodiments of this application, "unit" and "module" have the same meaning and can be used interchangeably.

[0308] Those skilled in the art will recognize that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. In the several embodiments provided in this application, it should be understood that the disclosed apparatus, devices, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0309] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0310] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0311] In the above embodiments, the functions of each functional unit can be implemented entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When the computer program instructions (programs) are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital video discs, DVDs), or semiconductor media (e.g., solid-state drives, SSDs), etc.

[0312] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the technology, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0313] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applied to a first communication device, the method includes: The device that provides communication services to the terminal is switched from the first communication device to the second communication device; Send a first message, the first message requesting that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requesting that the first communication device and the second communication device cooperate to provide computing services.

2. The method as described in claim 1, characterized in that, The first message indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the quality of service (QoS) requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

3. The method as described in claim 2, characterized in that, The first message also indicates the collaborative processing method.

4. The method according to any one of claims 1 to 3, characterized in that, The method further includes: Upon receiving a second message, when the first message requests a switch of the computing service from the first communication device to the second communication device, the second message indicates agreement to the switch, or indicates disagreement with the switch. When the first message requests the first communication device and the second communication device to cooperate in providing computing services, the second message indicates agreement to the first communication device and the second communication device cooperating in providing computing services, or the second message indicates disagreement with the first communication device and the second communication device cooperating in providing computing services.

5. The method as described in claim 4, characterized in that, When the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating to provide computing services, the second message indicates any of the following: computing service switching mode, reselection of target device, provision of computing services by the terminal, or provision of computing services by the terminal and the cloud server.

6. The method according to any one of claims 1 to 5, characterized in that, The method further includes: Send context information, which indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, computing data, or the execution log of the computing task.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: Send a third message, the third message requesting that the communication service be switched from the first communication device to the second communication device; A fourth message is received, indicating agreement to switch the communication service from the first communication device to the second communication device.

8. The method as described in claim 7, characterized in that, The third message indicates the switching time for the computing service.

9. The method as described in claim 7 or 8, characterized in that, Sending the first message includes: If preset conditions are met, a first message is sent. The preset conditions include one or more of the following: The historical calculation task is completed; the time elapsed since the third message was sent reaches a first duration; the terminal triggers the first communication device to send the first message.

10. The method as described in claim 8 or 9, characterized in that, The method further includes: Send a fifth message, which indicates the forwarding settings for the computing task. The forwarding settings include one or more of the following: a forwarding path, the address of each node on the forwarding path, or the identifier of the data stream. The forwarding path includes the first communication device and the second communication device.

11. The method as described in claim 7, characterized in that, The first message is sent before the fourth message is received.

12. A communication method, characterized in that, Applied to a second communication device, the method includes: Upon receiving a first message, the first message requests that the device providing computing services to the terminal be switched from the first communication device to the second communication device, or the first message requests that the first communication device and the second communication device cooperate to provide computing services, wherein the first communication device is the device that provided communication services to the terminal before the communication service switch, and the second communication device is the device that provides communication services to the terminal after the communication service switch.

13. The method as described in claim 12, characterized in that, The first message indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, the execution progress of the computing task, the computing resource requirements, the quality of service (QoS) requirements information corresponding to the computing service, the orchestration information of the computing task, or the execution logic of the computing task.

14. The method as described in claim 13, characterized in that, The first message also indicates the collaborative processing method.

15. The method according to any one of claims 12 to 14, characterized in that, The method further includes: A second message is sent when the first message requests the computing service to be switched from the first communication device to the second communication device. The second message indicates agreement to the switch, or disagreement with the switch. When the first message requests the first communication device and the second communication device to cooperate in providing computing services, the second message indicates agreement to the first communication device and the second communication device cooperating in providing computing services, or the second message indicates disagreement with the first communication device and the second communication device cooperating in providing computing services.

16. The method as described in claim 15, characterized in that, When the second message indicates disagreement with switching the computing service from the first communication device to the second communication device, or when the second message indicates disagreement with the first communication device and the second communication device cooperating to provide computing services, the second message indicates any of the following: computing service switching mode, reselection of target device, provision of computing services by the terminal, or provision of computing services by the terminal and the cloud server.

17. The method according to any one of claims 12 to 16, characterized in that, The method further includes: Receive context information, which indicates one or more of the following: the application corresponding to the computing service, the model corresponding to the computing service, the function corresponding to the computing service, computing data, or the execution log of the computing task.

18. The method according to any one of claims 12 to 17, characterized in that, The method further includes: Receive a third message, the third message requesting that the communication service be switched from the first communication device to the second communication device; A fourth message is sent, indicating agreement to switch the communication service from the first communication device to the second communication device.

19. The method as described in claim 18, characterized in that, The third message indicates the switching time for the computing service.

20. The method as described in claim 18 or 19, characterized in that, The method further includes: A fifth message is received, which indicates the forwarding settings for the computing task. The forwarding settings include one or more of the following: a forwarding path, the address of each node on the forwarding path, or the identifier of the data stream. The forwarding path includes the first communication device and the second communication device.

21. The method as described in claim 20, characterized in that, The method further includes: A sixth message is sent to the core network equipment, the sixth message indicating one or more of the following: forwarding path, the address of each node on the forwarding path, the identifier of the data flow, or indication information, the indication information indicating that the task session identifier and / or the QoS flow identifier corresponding to the computing service remains unchanged.

22. The method as described in claim 18, characterized in that, The first message is received before the fourth message is sent.

23. The method as described in claim 22, characterized in that, The method further includes: A seventh message is sent to the core network equipment, the seventh message indicating a modification to the forwarding path of the data flow.

24. A communication method, characterized in that, Applied to a terminal, the method includes: The device receives a first indication message from a first communication device, the first indication message indicating the device providing computing services to the terminal and / or the computing service switching mode, the computing service switching mode being the switching mode of the device providing computing services to the terminal when the device providing communication services to the terminal is switched from the first communication device to the second communication device.

25. The method as described in claim 24, characterized in that, The method further includes: Send first information to the first communication device, the first information indicating the supported computing service switching mode and / or computing resource requirements.

26. A communication device, characterized in that, It includes modules for implementing the method as described in any one of claims 1 to 11, or modules for implementing the method as described in any one of claims 12 to 23, or modules for implementing the method as described in claim 24 or 25.

27. A communication device, characterized in that, The method includes a processor configured to perform the method of any one of claims 1 to 11, or the method of any one of claims 12 to 23, or the method of claim 24 or 25, by means of logic circuits and / or by executing a computer program stored in a memory.

28. The apparatus according to claim 27, characterized in that, It also includes the memory.

29. A computer-readable storage medium, characterized in that, The storage medium stores a computer program or instructions, which, when executed by a computer, implement the method as described in any one of claims 1 to 11, or the method as described in any one of claims 12 to 23, or the method as described in claim 24 or 25.

30. A computer program product, characterized in that, The computer program product includes instructions that, when executed by a computer, implement the method as described in any one of claims 1 to 11, or the method as described in any one of claims 12 to 23, or the method as described in claim 24 or 25.

31. A communication system, characterized in that, It includes a first communication device and a second communication device, wherein the first communication device is used to implement the method as described in any one of claims 1 to 11, and the second communication device is used to implement the method as described in any one of claims 12 to 23.

32. The communication system according to claim 31, characterized in that, It also includes a terminal for implementing the method as described in claim 24 or 25.

Images