Communication method and related apparatus

Abstract

Embodiments of the present application provide a communication method and a related apparatus. The method is applied to a first access network device. The method comprises: sending a first request, wherein the first request comprises computing information of the first access network device, and the computing information of the first access network device indicates a computing capability supported by the first access network device; and receiving a first response, wherein the first response is a response to the first request, the first response comprises computing information of a second access network device, and the computing information of the second access network device indicates a computing capability supported by the second access network device. Thus, in scenarios where a terminal device switches between access network devices, a network side selects, for the terminal device, a target access network device that can provide both a computing service and a communication service.

Description

A communication method and related apparatus

[0001] This application claims priority to Chinese Patent Application No. 202411002159.7, filed on July 24, 2024, entitled "A Communication Method and Related Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communication technology, and in particular to a communication method and related apparatus. Background Technology

[0003] Cloud computing platforms provide computing services, and terminal devices can send data related to computing tasks (also known as computational tasks) to the cloud computing platform for execution. However, cloud computing platforms may experience high latency when executing computing tasks. Therefore, edge computing has been developed based on cloud computing. Edge computing refers to distributing computing tasks to edge computing nodes (simply called computing nodes) for execution. Because computing nodes are closer to users (e.g., terminal devices), edge computing has lower latency.

[0004] Because access network devices are closer to terminal devices, providing computing services to terminal devices by access network devices has the advantage of lower latency. Therefore, how access network devices can provide computing services to terminal devices has become a current research hotspot.

[0005] Switching between different access network devices is a common communication scenario for terminal devices. For example, a first access network device provides communication services to a terminal device, and after the terminal device switches to a second access network device, the second access network device provides communication services to the terminal device. Therefore, when a terminal device needs computing services from an access network device, ensuring that the computing tasks requested by the terminal device are not interrupted during switching scenarios is a pressing issue that needs to be addressed. Summary of the Invention

[0006] This application proposes a communication method and related apparatus, in which a first access network device and a second access network device can exchange their respective computing information, which indicates the computing services supported by the access network devices. This enables the network side to select a target access network device that can provide computing and communication services for the terminal device when it switches between access network devices, ensuring that the computing tasks requested by the terminal device are not interrupted.

[0007] In a first aspect, embodiments of this application propose a communication method applied to a first access network device. For example, the method is executed by the first access network device, which may be a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, chip system, module, control unit, circuit, or processor in the aforementioned device or apparatus, or a centralized unit (CU) and / or a distributed unit (DU). This application does not specifically limit the definition. It should be noted that in this application, the term "first access network device" can refer to the access network device itself, or to the chip, functional module, integrated circuit, or processor within the first access network device that performs the method provided in this application, or to the CU and / or DU included in the first access network device. This application does not specifically limit the definition. For example, the method executed by the first access network device is executed by the CU of the first access network device. In the first aspect and its possible implementations, the method is described using the execution of the first access network device as an example.

[0008] The method includes: a first access network device sending a first request, the first request including computing information of the first access network device, the computing information of the first access network device indicating the computing capabilities supported by the first access network device; the first access network device receiving a first response, the first response being a response to the first request, the first response including computing information of a second access network device, the computing information of the second access network device indicating the computing capabilities supported by the second access network device.

[0009] In one possible implementation, the first request is used to request the exchange of configuration data between the first access network device and the second access network device. The configuration data includes: calculation information of the first access network device and / or calculation information of the second access network device.

[0010] In another possible implementation, the first request is specifically used to request the exchange of application-level configuration data required for correct interoperability between the first access network device and the second access network device on the Xn-C interface. The application-level configuration data includes: computational information of the first access network device and / or computational information of the second access network device. For example, the first request and the first response belong to the Xn Setup procedure, the purpose of which is to exchange application-level configuration data needed for two NG-RAN (New Radio Access Network, such as the first and second access network devices) nodes to interoperate correctly over the Xn-C interface.

[0011] It should be noted that the Xn-C interface is the interface between the first access network device and the second access network device. The interface between the first access network device and the second access network device can also be other interfaces besides the Xn-C interface. This application embodiment does not limit this.

[0012] In one example, the first request could be an Xn setup request message, and correspondingly, the first response could be an Xn setup response message.

[0013] One example scenario is as follows: During the deployment of a first access network device, the first access network device initiates a connection with its neighboring site (i.e., a second access network device). During this connection initialization process, the first access network device sends a first request to the second access network device to exchange their respective computing information.

[0014] Optionally, when the computing power of the first access network device changes (or is updated), the first access network device may also notify the second access network device of the updated computing information, which indicates the updated computing power supported by the first access network device.

[0015] In another example, the first request could be a configuration update message, such as an NG-RAN node configuration update message. Correspondingly, the first response could also be a configuration update message.

[0016] In the above technical solution, the first access network device and the second access network device can exchange their respective computing information, which indicates the computing services supported (or provided) by the access network devices. The first access network device can select a suitable target access network device to execute the computing task based on the computing information of the second access network device. For example, during the process of a terminal device switching from the first access network device to another access network device, if the terminal device needs computing services from an access network device, the first access network device can select a suitable target access network device for the terminal device based on the computing information of the second access network device. The target access network device belongs to the second access network device. This ensures that after the terminal device switches to the target access network device, the target access network device can provide computing services to the terminal device, ensuring that the computing tasks required by the terminal device can be successfully executed, guaranteeing that the computing tasks requested by the terminal device are not interrupted, and improving the user experience.

[0017] In conjunction with the first aspect, in one possible implementation of the first aspect, the computing information of the first access network device includes: identification information of the computing node associated with the first access network device, the computing node being used to provide computing services; first indication information of the first access network device, the first indication information of the first access network device indicating whether the first access network device supports providing computing services; computing resource information of the first access network device, the computing resource information of the first access network device indicating the computing resources related to the computing services; or, computing load information of the first access network device, the computing load information of the first access network device indicating the load status of the computing resources provided by the first access network device.

[0018] The computing information of the second access network device includes: identification information of the computing node associated with the second access network device, the computing node being used to provide computing services; first indication information of the second access network device, the first indication information of the second access network device indicating whether the second access network device supports providing computing services; computing resource information of the second access network device, the computing resource information of the second access network device indicating the computing resources related to the computing services; or, computing load information of the second access network device, the computing load information of the second access network device indicating the load status of the computing resources provided by the second access network device.

[0019] The computing service in this application embodiment refers to the computing service provided for the application service, which includes, but is not limited to, at least one of the following: video decoding service, image processing service, image recognition service, speech recognition service, machine translation service, gesture recognition service, autonomous driving service, route planning service, neural network model inference service, or neural network model training service, etc.

[0020] In one example, the computing information of the first access network device includes at least: first indication information of the first access network device; the computing information of the second access network device includes at least: first indication information of the second access network device. The first indication information indicates whether the first or second access network device supports providing computing services.

[0021] In the above technical solution, the computing information can indicate the various types of computing capabilities of the access network device, and based on the computing information, the target access network device to be switched can be determined for the terminal device, ensuring that the computing tasks requested by the terminal device can be executed by the target access network device, thus guaranteeing the normal operation of the terminal device.

[0022] In conjunction with the first aspect, in one possible implementation of the first aspect, the computing information of the first access network device further includes: identification information of one or more cells managed by the first access network device; wherein, the identification information of the computing node associated with the first access network device is specifically used to indicate the computing node associated with the one or more cells managed by the first access network device, the first indication information of the first access network device is specifically used to indicate whether the one or more cells managed by the first access network device support providing computing services, the computing resource information of the first access network device is specifically used to indicate the relevant computing resources for providing computing services in the one or more cells managed by the first access network device, and / or, the computing load information of the first access network device is specifically used to indicate the load status of the computing resources provided by the one or more cells managed by the first access network device;

[0023] The computing information of the second access network device also includes: identification information of one or more cells managed by the second access network device; wherein, the identification information of the computing node associated with the second access network device is specifically used to indicate the computing node associated with one or more cells managed by the second access network device; the first indication information of the second access network device is specifically used to indicate whether one or more cells managed by the second access network device support providing computing services; the computing resource information of the second access network device is specifically used to indicate the relevant computing resources for providing computing services in one or more cells managed by the second access network device; and / or, the computing load information of the second access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the second access network device.

[0024] In the above technical solution, when the calculation information also includes the cell's identification information, the calculation information can also indicate the various types of computing capabilities of the cell. Based on this calculation information, candidate target cells can be determined for the terminal device, ensuring that the computing tasks requested by the terminal device can be executed by the candidate target cell, thus guaranteeing the normal operation of the terminal device.

[0025] In conjunction with the first aspect, in one possible implementation of the first aspect, the computing resource information includes any one or more of the following: hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information.

[0026] The hardware resource information of the first access network device indicates the hardware resources of the computing node associated with the first access network device. This processing capability information can indicate the floating-point arithmetic capability of the computing node. It can also indicate the average processing latency of the computing node when processing computing tasks. Storage capability information indicates the amount of storage space available to the computing node. Transmission resource information indicates the total transmission bandwidth of the computing node, and / or the available transmission bandwidth. Software resource information can indicate the various types of software, operating systems, application services, artificial intelligence (AI) algorithms, or neural network models that the computing node supports running.

[0027] In conjunction with the first aspect, in one possible implementation of the first aspect, the computational load information includes any one or more of the following: load information of processing resources, load information of storage resources, or load information of transmission resources.

[0028] For example, computational load information indicates the memory utilization, transmission bandwidth utilization, and / or processing resource utilization of the computing node.

[0029] In conjunction with the first aspect, in one possible implementation of the first aspect, a second request is sent to the target access network device. The second request instructs the terminal device to request a handover to the target access network device, which belongs to one or more second access network devices. The second request further includes: context information of the computing task that the terminal device requests to execute. The context information of the computing task includes any one or more of the following: identification information of the computing task, identification information of the application, the application being an application related to the computing task, bearer information of the computing task, the bearer information indicating the transmission path of the data carrying the computing task, the transmission path including: Data Radio Bearer (DRB), and / or Quality of Service (QoS) flow, identification information of the computing node supporting the execution of the computing task, or, second indication information indicating that the computing task needs to be switched to the target access network device to continue execution.

[0030] In the above technical solution, the second request sent by the first access network device to the target access network device may also carry context information of the computing task. This allows the target access network device to determine whether to allow the terminal device to access based on the context information of the computing task, ensuring that the terminal device can obtain computing services from the access network device after handover and guaranteeing that the terminal device can continue to execute computing tasks in the handover scenario.

[0031] In conjunction with the first aspect, in one possible implementation of the first aspect, the context information of the computation task also includes any one or more of the following: computation state information of the neural network model related to the computation task, type information of the neural network model, parameter information of the neural network model, key-value storage (KV) cache information of the neural network model, information of one or more intermediate layers included in the neural network model, initial input feature information of the neural network model, or output feature information of one or more intermediate layers of the neural network model.

[0032] In the above technical solution, when the computation task is a computation task related to a neural network model (e.g., a training task), the context information of the computation task may also include information related to the neural network model. This allows the target access network device to continue executing the computation task based on this context information after the terminal device switches to the target access network device, ensuring the smooth execution of the computation task. When the computation task is a training task for a neural network model, it can also improve the training effect of the neural network model.

[0033] In conjunction with the first aspect, in one possible implementation of the first aspect, the method further includes: receiving a second response from the target access network device, the second response being a response to the second request, the second response indicating the reason for the failure of the terminal device to switch to the target access network device.

[0034] In one example, the reasons for a handover failure include: the terminal device is not allowed to access the target access network device in this requested handover, or the terminal device is prohibited from accessing the target access network device in this and future requested handovers.

[0035] In another example, the reasons for the handover failure include: the target access network device does not support providing computing services, the target access network device has insufficient computing resources, the target access network device does not support the computing task requested by the terminal device, or the target access network device has no connection with a computing node that supports performing computing tasks.

[0036] The specific reason for the switching failure can be indicated in a variety of ways, including but not limited to one or more of the following: reason value, indication information, field, or flag bit.

[0037] In the above technical solution, the target access network device can provide feedback on the reasons why various terminal devices failed to switch to the target access network device, so that the first access network device can reselect an access network device to be switched to for the terminal device.

[0038] In conjunction with the first aspect, in one possible implementation of the first aspect, the method further includes: a first access network device receiving measurement results from a terminal device, the measurement results indicating the measurement results of the terminal device for one or more neighboring cells; then, the first access network device determining a target access network device from one or more second access network devices based on the measurement results and calculation information from one or more second access network devices.

[0039] In the above technical solution, the first access network device can combine the measurement results of the terminal device and the calculation information of one or more second access network devices to determine the target access network device for the terminal device, thereby improving the user experience of the terminal device.

[0040] Secondly, embodiments of this application propose a communication method applied to a first access network device, for example, executed by the first access network device. The first access network device may be a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, chip system, module, control unit, circuit, or processor in the aforementioned device or apparatus, or a centralized unit (CU) and / or a distributed unit (DU). This application does not specifically limit the definition. It should be noted that in this application, the term "first access network device" can refer to the access network device itself, or to the chip, functional module, integrated circuit, or processor within the first access network device that performs the method provided in this application, or to the CU and / or DU included in the first access network device. This application does not specifically limit the definition. For example, the method executed by the first access network device is executed by the CU of the first access network device. In the second aspect and its possible implementations, the method being executed by the first access network device is described as an example. The method includes: sending a second request to a target access network device, the second request instructing a terminal device to request a switch to the target access network device, the second request including context information of a computing task requested by the terminal device to be executed; and receiving a second response from the target access network device, the second response being a response to the second request.

[0041] The computing service in this application embodiment refers to the computing service provided for the application service, which includes, but is not limited to, at least one of the following: video decoding service, image processing service, image recognition service, speech recognition service, machine translation service, gesture recognition service, autonomous driving service, route planning service, neural network model inference service, or neural network model training service, etc.

[0042] In the above technical solution, the second request sent by the first access network device to the target access network device may also carry context information of the computing task. This allows the target access network device to determine whether to allow the terminal device to access based on the context information of the computing task, ensuring that the terminal device can obtain computing services from the access network device after handover, guaranteeing that the terminal device can continue to execute computing tasks in handover scenarios, ensuring that the computing tasks requested by the terminal device are not interrupted, and improving the user experience.

[0043] Thirdly, embodiments of this application propose a communication method applied to a target access network device, for example, executed by the target access network device. The target access network device may be a device or apparatus with a chip, or a device or apparatus with integrated circuits, or a chip, chip system, module, control unit, circuit, or processor in the aforementioned device or apparatus, or a centralized unit (CU) and / or distributed unit (DU). This application does not specifically limit the definition. It should be noted that in this application, when referring to a target access network device, it can refer to the access network device itself, or to the chip, functional module, integrated circuit, or processor within the target access network device that performs the method provided in this application, or to the CU and / or DU included in the target access network device. This application does not specifically limit the definition. For example, the method executed by the target access network device is executed by the CU of the target access network device. In the third aspect and its possible implementations, the method is described as being executed by the target access network device. The method includes:

[0044] The terminal device receives a second request from a first access network device. The second request instructs the terminal device to request a switch to a target access network device and requests the target access network device to provide computing and communication services to the terminal device. The second request includes context information of the computing task that the terminal device requests to perform. Based on the second request and the computing information of the target access network device, the terminal device sends a second response to the first access network device. The computing information of the target access network device indicates the computing capabilities supported by the target access network device.

[0045] The target access network device supporting the provision of communication and computing services to the terminal device can also be replaced by: the target access network device being an access network device that supports executing the computing tasks requested by the terminal device; or the computing resources (or computing services) provided by the target access network device being able to execute the computing tasks requested by the terminal device; or the computing nodes associated with the target access network device being able to execute the computing tasks requested by the terminal device; or the target access network device being able to meet the computing capacity (or computing resources, or computing services, or quality of service) requirements of the terminal device when requesting to execute the computing task.

[0046] In the above technical solution, the second request sent by the first access network device to the target access network device may also carry context information of the computing task. This allows the target access network device to determine whether to allow the terminal device to access based on the context information of the computing task, ensuring that the terminal device can obtain computing services from the access network device after handover, guaranteeing that the terminal device can continue to execute computing tasks in handover scenarios, ensuring that the computing tasks requested by the terminal device are not interrupted, and improving the user experience.

[0047] In conjunction with the third aspect, in any possible implementation of the third aspect, the computing information of the target access network device includes any one or more of the following: identification information of the computing node associated with the target access network device, the computing node being used to provide computing services, first indication information of the target access network device, the first indication information of the target access network device indicating whether the target access network device supports providing computing services, computing resource information of the target access network device, the computing resource information of the target access network device indicating the computing resources related to the computing services, or, computing load information of the target access network device, the computing load information of the target access network device indicating the load status of the computing resources provided by the target access network device.

[0048] In the above technical solution, the computing information can indicate the various types of computing capabilities of the target access network device. The target access network device performs access judgment on the terminal device based on the computing information, ensuring that the terminal device can perform computing tasks normally after accessing the target access network device, thus guaranteeing the normal operation of the terminal device.

[0049] In conjunction with the third aspect, in any possible implementation of the third aspect, the computing information of the target access network device further includes: identification information of one or more cells managed by the target access network device; wherein, the first indication information of the target access network device is specifically used to indicate whether one or more cells managed by the target access network device support providing computing services, the computing resource information of the target access network device is specifically used to indicate the relevant computing resources for providing computing services in one or more cells managed by the target access network device, and / or, the computing load information of the target access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the target access network device.

[0050] In the above technical solution, the computing information can also indicate various types of computing capabilities at the cell level. The target access network device performs access judgment on the terminal device based on the computing information, ensuring that the computing tasks requested by the terminal device can be executed by the target cell managed by the target access network device, thus guaranteeing the normal operation of the terminal device.

[0051] In conjunction with the third aspect, in any possible implementation of the third aspect, the computing resource information includes any one or more of the following: hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information.

[0052] The hardware resource information of the target access network device indicates the hardware resources of the computing node associated with the target access network device. This processing capability information can indicate the floating-point arithmetic capability of the computing node. It can also indicate the average processing latency of the computing node when processing computing tasks. Storage capability information indicates the amount of storage space available to the computing node. Transmission resource information indicates the total transmission bandwidth of the computing node, and / or the available transmission bandwidth. Software resource information indicates the types of software, operating systems, application services, artificial intelligence algorithms, or neural network models that the computing node supports running.

[0053] In conjunction with the third aspect, in any possible implementation of the third aspect, the computational load information includes any one or more of the following: load information of processing resources, load information of storage resources, or load information of transmission resources.

[0054] In conjunction with the second or third aspect, in any possible implementation of the second or third aspect, the context information of the computing task includes any one or more of the following: identification information of the computing task, identification information of the application, the application being an application related to the computing task, bearer information of the computing task, the bearer information indicating the transmission path of the data carrying the computing task, the transmission path including: data radio bearer (DRB), and / or, quality of service flow (QoS flow), identification information of the computing node supporting the execution of the computing task, or, second indication information, the second indication information indicating that the computing task needs to switch to the target access network device to continue execution.

[0055] In conjunction with the second or third aspect, in any possible implementation of the second or third aspect, the context information of the computation task further includes any one or more of the following: computation state information of the neural network model related to the computation task, type information of the neural network model, parameter information of the neural network model, key-value storage (KV) cache information of the neural network model, information of one or more intermediate layers included in the neural network model, initial input feature information of the neural network model, or output feature information of one or more intermediate layers of the neural network model.

[0056] In the above technical solution, when the computation task is a computation task related to a neural network model (e.g., a training task), the context information of the computation task may also include information related to the neural network model. This allows the target access network device to continue executing the computation task based on this context information after the terminal device switches to the target access network device, ensuring the smooth execution of the computation task. When the computation task is a training task for a neural network model, it can also improve the training effect of the neural network model.

[0057] In conjunction with the second or third aspect, in any possible implementation of the second or third aspect, the reasons for handover failure include: not allowing the terminal device to access the target access network device in this requested handover, or prohibiting the terminal device from accessing the target access network device in this and future requested handovers.

[0058] In another example, the reasons for the handover failure include: the target access network device does not support providing computing services, the target access network device has insufficient computing resources, the target access network device does not support the computing task requested by the terminal device, or the target access network device has no connection with a computing node that supports performing computing tasks.

[0059] The specific reason for the switching failure can be indicated in a variety of ways, including but not limited to one or more of the following: reason value, indication information, field, or flag bit.

[0060] In the above technical solution, the target access network device can provide feedback on the reasons why various terminal devices failed to switch to the target access network device, so that the first access network device can reselect an access network device to be switched to for the terminal device.

[0061] Fourthly, this application provides a communication device suitable for a first access network device. For example, the communication device may be the first access network device itself, or a component within the first access network device (e.g., a processor, circuit, chip, or chip system). The communication device may include modules, units, or means corresponding to the methods described in the first aspect and any possible implementation thereof. These modules, units, or means may be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the aforementioned functions.

[0062] In the fourth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the first aspect and achieve the corresponding technical effects. For details, please refer to the first aspect, which will not be repeated here.

[0063] Fifthly, this application provides a communication device suitable for a first access network device. For example, the communication device may be the first access network device itself, or a component within the first access network device (e.g., a processor, circuit, chip, or chip system). The communication device may include modules, units, or means corresponding to the methods described in the second aspect and any possible implementation thereof. These modules, units, or means may be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the aforementioned functions.

[0064] In the fifth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the second aspect and achieve the corresponding technical effects. For details, please refer to the second aspect, which will not be repeated here.

[0065] Sixthly, this application provides a communication device suitable for a target access network device. For example, the communication device may be the target access network device itself, or a component within the target access network device (e.g., a processor, circuit, chip, or chip system). The communication device may include modules, units, or means corresponding to the methods described in the third aspect and any possible implementation thereof. These modules, units, or means may be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units corresponding to the aforementioned functions.

[0066] In the sixth aspect of this application, the constituent modules of the communication device can also be used to perform the steps executed in various possible implementations of the third aspect and achieve the corresponding technical effects. For details, please refer to the third aspect, which will not be repeated here.

[0067] In a seventh aspect, this application provides a communication device including at least one processor coupled to a memory; the memory is used to store a program or instructions; the at least one processor is used to execute the program or instructions to cause the device to implement the method described in any possible implementation of any of the first to third aspects. Optionally, the communication device may include the memory.

[0068] In an eighth aspect, this application provides a communication device including at least one logic circuit and an input / output interface; the logic circuit is configured to perform the method described in any of the possible implementations of the first to third aspects described above.

[0069] In a ninth aspect, this application provides a communication system that includes the aforementioned first access network device and / or second access network device.

[0070] In conjunction with the ninth aspect, in one possible implementation of the ninth aspect, the communication system includes the communication device described in the fourth aspect.

[0071] In a tenth aspect, this application provides a communication system that includes the aforementioned first access network device and target access network device.

[0072] In conjunction with the tenth aspect, in one possible implementation of the tenth aspect, the communication system includes the communication device of the fifth aspect and the communication device of the sixth aspect.

[0073] Eleventhly, this application provides a computer-readable storage medium for storing one or more computer-executable instructions, which, when executed by a processor, perform the method as described in any possible implementation of any of the first to third aspects above.

[0074] In a twelfth aspect, this application provides a computer program product (or computer program) that, when executed by a processor, performs the method described in any possible implementation of any of the first to third aspects.

[0075] In a thirteenth aspect, this application provides a chip or chip system including at least one processor for supporting a communication device in implementing the methods described in any possible implementation of any of the first to third aspects. For example, the chip may be a baseband chip, a modem chip, a system-on-chip (SoC) chip containing a modem core, a system-in-package (SIP) chip, or a communication module, etc.

[0076] In one possible design, the chip or chip system may further include a memory for storing program instructions and data necessary for the communication device. The chip system may be composed of chips or may include chips and other discrete devices. Optionally, the chip system may also include interface circuitry that provides program instructions and / or data to the at least one processor.

[0077] The technical effects of any of the design methods in aspects four through thirteen can be found in the technical effects of the different design methods in aspects one through three above, and will not be repeated here. Attached Figure Description

[0078] Figures 1a to 1e are schematic diagrams of the AI ​​processing involved in this application;

[0079] Figure 2 is a schematic diagram of a communication system according to an embodiment of this application;

[0080] Figure 3a is a schematic diagram of another communication system in an embodiment of this application;

[0081] Figure 3b is a schematic diagram of another communication system in an embodiment of this application;

[0082] Figure 4 is a schematic diagram of another communication system in the embodiments of this application;

[0083] Figure 5 is a schematic diagram of another communication system in the embodiments of this application;

[0084] Figure 6 is a schematic diagram of the application architecture involving the RIC module under the ORAN architecture;

[0085] Figure 7 is a structural schematic diagram of an access network device according to an embodiment of this application;

[0086] Figure 8 is a schematic diagram of a communication scenario involved in an embodiment of this application;

[0087] Figure 9 is a flowchart illustrating one embodiment of the communication method in this application.

[0088] Figure 10a is a schematic flowchart of another embodiment of the communication method in this application;

[0089] Figure 10b is a flowchart illustrating another embodiment of the communication method in this application.

[0090] Figure 11 is a schematic diagram of a communication device according to an embodiment of this application;

[0091] Figure 12 is another structural schematic diagram of the communication device according to an embodiment of this application;

[0092] Figure 13 is another structural schematic diagram of the communication device according to an embodiment of this application. Detailed Implementation

[0093] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a particular order or sequence. It should be understood that such terms are interchangeable where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0094] It should be understood that the term "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be single or multiple. Additionally, the character " / " in this document generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, "at least one of the following" or similar expressions in this document are used to represent any combination of the listed items; for example, at least one of A, B, and / or C can represent the following six situations: A alone, B alone, C alone, A and B simultaneously, B and C simultaneously, A and C simultaneously, and A, B, and C simultaneously, where A, B, and C can be single or multiple.

[0095] First, some terms used in the embodiments of this application will be explained to facilitate understanding by those skilled in the art.

[0096] (1) Configuration and Pre-configuration: In this application, both configuration and pre-configuration are used. Configuration refers to the network device sending configuration information or parameter values ​​of some parameters to the terminal device through messages or signaling, so that the terminal device can determine the communication parameters or resources during transmission based on these values ​​or information. Pre-configuration is similar to configuration; it can be parameter information or parameter values ​​that the network device and the terminal device have negotiated in advance, or it can be parameter information or parameter values ​​that the network device or the terminal device uses as specified by the standard protocol, or it can be parameter information or parameter values ​​that are pre-stored in the network device or the terminal device. This application does not limit this.

[0097] Furthermore, these values ​​and parameters can be changed or updated.

[0098] (2) The terms "system" and "network" in the embodiments of this application can be used interchangeably. "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the related objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, "at least one of A, B and C" includes A, B, C, AB, AC, BC or ABC. And, unless otherwise specified, the ordinal numbers such as "first" and "second" mentioned in the embodiments of this application are used to distinguish multiple objects and are not used to limit the order, sequence, priority or importance of multiple objects.

[0099] (3) In the embodiments of this application, "send" and "receive" indicate the direction of signal transmission. For example, "send information to XX" can be understood as the destination of the information being XX, which may include sending directly through the air interface or sending indirectly through the air interface by other units or modules. "Receive information from YY" can be understood as the source of the information being YY, which may include receiving directly from YY through the air interface or receiving indirectly from YY through the air interface by other units or modules. "Send" can also be understood as the "output" of the chip interface, and "receive" can also be understood as the "input" of the chip interface.

[0100] In other words, sending and receiving can occur between devices, such as between network devices and terminal devices, or within a device, such as between components, modules, chips, software modules, or hardware modules within the device via buses, wiring, or interfaces.

[0101] It is understandable that information may undergo necessary processing, such as encoding and modulation, between the source and destination, but the destination can understand the valid information from the source. Similar statements in this application can be interpreted in a similar way and will not be elaborated further.

[0102] (4) Artificial Intelligence (AI).

[0103] AI can endow machines with human-like intelligence, for example, allowing them to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) neural network models using training data. This neural network model can also be called an AI model, a large AI model, a large language model (LLMs), or simply a model. This model represents the mapping from input to output. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0104] Machine learning can include supervised learning, unsupervised learning, and reinforcement learning. Unsupervised learning can also be called learning without supervision.

[0105] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and then expresses this learned mapping relationship using an AI model. The process of training the machine learning model is the process of learning this mapping relationship. During training, sample values ​​are input into the model to obtain the model's predicted values, and the model parameters are optimized by calculating the error between the model's predicted values ​​and the sample labels (ideal values). After the mapping relationship is learned, it can be used to predict new sample labels. The mapping relationship learned in supervised learning can include linear or non-linear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0106] Unsupervised learning relies on collected sample values ​​to discover inherent patterns within the samples themselves. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals, meaning the model learns the mapping relationship from sample to sample; this is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0107] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with its environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment, obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is to find the decision action that maximizes the cumulative reward over a relatively long period. Training in reinforcement learning is achieved through iterative interaction with the environment.

[0108] Neural networks (NNs) are a specific model in machine learning techniques. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while deep learning communication systems based on neural networks can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0109] The idea behind neural networks comes from the neuronal structure of the brain. For example, each neuron performs a weighted summation of its input values ​​and outputs the result through an activation function.

[0110] Figure 1a shows a schematic diagram of a neuron structure. Assume the input to the neuron is x = [x0, x1, ..., x...]. n The weights corresponding to each input are w = [w, w1, ..., w2]. n ], where n is a positive integer, w i and x i It can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. i As x i The weights are used to assign weights to x. i Weighting is applied. The bias for the weighted summation of the input values ​​is, for example, b. Activation functions can take many forms. Assuming a neuron's activation function is y = f(z) = max(0, z), then the neuron's output is: For example, if the activation function of a neuron is y = f(z) = z, then the output of that neuron is y = Here, b can be any possible type, such as a decimal, an integer (e.g., 0, a positive integer, or a negative integer), or a complex number. The activation functions of different neurons in a neural network can be the same or different.

[0111] Furthermore, neural networks generally consist of multiple layers, each of which may include one or more neurons. Increasing the depth and / or width of a neural network can improve its expressive power, providing more powerful information extraction and abstract modeling capabilities for complex systems. The depth of a neural network can refer to the number of layers it includes, and the number of neurons in each layer can be called the width of that layer. In one implementation, a neural network includes an input layer and an output layer. The input layer processes the received input information through neurons and passes the processing result to the output layer, which then obtains the output of the neural network. In another implementation, a neural network includes an input layer, hidden layers, and an output layer. The input layer processes the received input information through neurons and passes the processing result to the hidden layer. The hidden layer calculates the received processing result and passes the calculation result to the output layer or the next adjacent hidden layer, ultimately obtaining the output of the neural network. A neural network may include one hidden layer or multiple sequentially connected hidden layers, without limitation.

[0112] Neural networks, for example, are deep neural networks (DNNs). Depending on how the network is constructed, DNNs can include feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs).

[0113] Figure 1b is a schematic diagram of an FNN network. A characteristic of FNN networks is that neurons in adjacent layers are completely connected pairwise. This characteristic makes FNNs typically require a large amount of storage space, leading to high computational complexity.

[0114] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (e.g., discrete sampling along a time axis) and image data (e.g., two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (e.g., people and objects in an image represent different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0115] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. The input to an RNN includes the current input value and its own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0116] In the model training process described above for machine learning, a loss function can be defined. The loss function describes the difference or discrepancy between the model's output value and the ideal target value. The loss function can be expressed in various forms, and there are no restrictions on its specific form. The model training process can be viewed as follows: by adjusting some or all of the model's parameters, the value of the loss function is made to be less than a threshold value or to meet the target requirement.

[0117] A model can also be called an AI model, a rule, or other names. An AI model can be considered a specific method for implementing AI functions. An AI model represents the mapping relationship or function between the model's input and output. AI functions can include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result publication, etc. AI functions can also be called AI (related) operations or AI-related functions.

[0118] The implementation process of a fully connected neural network will be described below with reference to the accompanying drawings. A fully connected neural network is also called a multilayer perceptron (MLP).

[0119] As shown in Figure 1c, an MLP consists of an input layer (left side), an output layer (right side), and multiple hidden layers (middle). Each layer of an MLP contains several nodes, called neurons. Neurons in adjacent layers are connected pairwise.

[0120] Optionally, considering neurons in two adjacent layers, the output h of the next layer's neurons is the weighted sum of all neurons x in the previous layer connected to it and passed through an activation function, which can be expressed as: h = f(wx + b).

[0121] Where w is the weight matrix, b is the bias vector, and f is the activation function.

[0122] Alternatively, the output of the neural network can be recursively expressed as: y = f n (w n f n-1 (…)+b n ).

[0123] Where n is the index of the neural network layer, n is greater than or equal to 1 and less than or equal to N, where N is the total number of layers in the neural network.

[0124] In other words, a neural network can be understood as a mapping from an input data set to an output data set. Neural networks are typically initialized randomly; the process of obtaining this mapping from random values ​​w and b using existing data is called training the neural network.

[0125] Optionally, the training process can be carried out by using a loss function to evaluate the output of the neural network.

[0126] As shown in Figure 1d, the error can be backpropagated, and the neural network parameters (including w and b) can be iteratively optimized using gradient descent until the loss function reaches its minimum, which is the "better point (e.g., the optimal point)" in Figure 1d. It can be understood that the neural network parameters corresponding to the "better point (e.g., the optimal point)" in Figure 1d can be used as the neural network parameters in the trained AI model information.

[0127] Alternatively, the gradient descent process can be represented as:

[0128] Where θ represents the parameters to be optimized (including w and b), L is the loss function, and η is the learning rate, controlling the step size of gradient descent. This represents the differentiation operation. This indicates taking the derivative of θ with respect to L.

[0129] Alternatively, the backpropagation process can utilize the chain rule for partial derivatives.

[0130] As shown in Figure 1e, the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer, and can be expressed as:

[0131] Among them, w ij Let s be the weight of the connection between node j and node i. i The weighted sum of the inputs at node i.

[0132] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0133] The following describes some possible communication systems to which this application applies. It should be understood that this application also applies to other communication systems, and no specific limitations are imposed by this application.

[0134] Figure 2 is a schematic diagram of a communication system according to an embodiment of this application. Referring to Figure 2, the communication system includes a terminal device 101, an access network device 102, an access network device 103, a computing node 104, and a computing node 105. The computing node management function 106 can be deployed on the core network side or on the access network side.

[0135] Terminal device 101 communicates with access network devices (access network device 102 or access network device 103 as shown in Figure 2) via the Uu interface. Access network devices 102 and 103 are access network devices in a New Radio (NR) communication system. In the communication system, access network devices communicate with each other via the Xn interface.

[0136] Access network equipment (such as access network equipment 102 or access network equipment 103 in Figure 2) is a device deployed in a wireless access network to provide wireless communication functions for terminal devices.

[0137] The computing node (including computing node 104 and / or computing node 105) can connect to the access network device without using the user plane function (UPF).

[0138] Computing node 104 or computing node 105 refers to a node used to provide computing resources (or provide computing services) and is responsible for executing computing tasks. In this embodiment, computing tasks include, but are not limited to, one or more of the following: image rendering tasks, video decoding tasks, image processing tasks, image recognition tasks, speech recognition tasks, machine translation tasks, gesture recognition tasks, autonomous driving tasks, route planning tasks, neural network model inference tasks, or neural network model training tasks, etc.

[0139] In this embodiment, an access network device may be associated with one or more computing nodes, and the access network device obtains computing resources through multiple computing nodes. Alternatively, multiple access network devices may have a management relationship with a single computing node, and the computing resources provided by the computing node may be allocated to multiple access network devices for use.

[0140] For ease of understanding, please refer to Figure 3a as an example. Figure 3a is a schematic diagram of another structure of the communication system in this embodiment of the application. Access network device 1 is associated with computing nodes 1, 2, and 3. This association means that there is a physical connection between the access network device and the computing nodes, allowing the access network device to use the computing resources provided by the computing nodes and to request the computing nodes to perform computing tasks. Access network device 1 can use the computing resources provided by computing nodes 1, 2, and 3, and the computing tasks that access network device 1 needs to perform can be performed by computing nodes 1, 2, and / or 3. Access network device 2 is associated with computing node 3. Access network device 2 can use the computing resources provided by computing node 3, and the computing tasks that access network device 2 needs to perform can be performed by computing node 3.

[0141] It should be noted that the names of computing nodes 104 and 105 may change as the communication system evolves. Any functional network element with a similar function to computing nodes 104 and 105 can be understood as computing nodes 104 and 105 in this application. For example, a computing node can also be called a task execution function (TEF), a far-edge intelligent node (FeIN), a far-edge computing node (FeCN), a task execution node, a computing execution function (CEF), a computing power node, a computing power device, a computing power unit, a computing power board, a computing execution node, an edge computing node, a computing function node, a computing task node, a computing task execution node, a computing function, a computing task function, or a computing task execution function, etc. This application does not limit the specific name.

[0142] The compute node management function 106 is used to manage compute connections. For example, the execution of a compute task involves data transmission between a terminal and a compute node. The compute node management function 106 is also used to manage the processing of connections between the terminal and the compute node. For example, in one implementation, a Protocol Data Unit (PDU) session or a compute-specific session can be established between the terminal and the compute node; in this case, the compute node management function 106 manages the session, such as establishing, modifying, and / or releasing the session. As another example, the compute node management function 106 is used to select a compute node for a compute task. Furthermore, the compute node management function 106 selects a compute node for the access network device based on the compute task to be executed.

[0143] In one possible implementation, the computing node management function 106 is set up separately as a core network element.

[0144] In another possible implementation, the compute node management function 106 is deployed within the access and mobility management function (AMF) or the session management function (SMF), with the AMF or SMF providing the relevant functions of the compute node management function 106. In other words, the compute node management function 106 is co-located with the AMF or SMF.

[0145] In another possible implementation, the compute node management function 106 is deployed on compute node 104 or compute node 105. In other words, compute node 104 or compute node 105 itself provides management functions, and compute node management function 106 serves as the control plane for compute node 104 or compute node 105.

[0146] In another possible implementation, the computing node management function 106 is deployed in the access network device, serving as a function of the access network device to manage computing nodes.

[0147] For ease of understanding, please refer to Figure 3b, which is another structural schematic diagram of the communication system in an embodiment of this application. The connection between the access network device and computing node 1 or computing node 2 is used to transmit user plane data. The computing node management function is responsible for managing the connection between the access network device and the computing node, and can also be used to select computing nodes for computing tasks. For example, if a terminal device requests a computing task that computing node 1 can execute, but computing node 2 cannot, the computing node management function establishes a connection between the terminal device and computing node 1, so that after the access network receives the computing task submitted by the terminal device, it can submit it to computing node 1 for execution.

[0148] It should be noted that the name of the computing node management function 106 may change as the communication system evolves. Any network element with a similar name to the computing node management function 106 can be understood as the computing node management function 106 of this application. For example, the computing node management function 106 can also be a task management function (TMF), a computing management function (CMF), a task management node, a computing management function, a computing task management function, a computing task management node, a computing power management function, or a computing power management node, etc. The embodiments of this application do not limit this.

[0149] It should be noted that the communication system shown in Figure 2 may include more or fewer computing nodes, and no restrictions are imposed here.

[0150] It should be noted that the name AMF in the communication system shown in Figure 2 above is merely an example. The name of AMF may change as the communication system evolves. Any functional network element with a name similar to AMF can be understood as the AMF of this application. For example, AMF can also be called a mobility management network element or mobility management function, etc., and this application does not limit the specific name. The name UPF may change as the communication system evolves. Any functional network element with a name similar to UPF can be understood as the UPF of this application. For example, UPF can also be called a user plane network element or user plane management network element, etc., and this application does not limit the specific name.

[0151] Please refer to Figure 4, which is a schematic diagram of another communication system according to an embodiment of this application. In the communication system shown in Figure 4, the access network device establishes a transmission link (or establishes a transmission path, or establishes a connection, or establishes an association) with computing nodes 1 to M, where M is an integer greater than or equal to 1. In other words, the computing nodes are external devices relative to the access network device, and the computing nodes and the access network device are independent of each other. For example, the computing nodes, as external service cards or computing cards, establish a connection with the access network device through an interface.

[0152] Please refer to Figure 5, which is a schematic diagram of another communication system according to an embodiment of this application. In the communication system illustrated in Figure 5, the access network device establishes a transmission link (or establishes a transmission path, or establishes a connection, or establishes an association) with computing nodes 1 to M, where M is an integer greater than or equal to 1. In other words, the computing nodes are built-in devices relative to the access network device; the access network device has computing nodes installed inside it, and the computing nodes are deployed within the access network device. For example, the computing unit (e.g., a processor or computing card) built into the access network device serves as a computing node.

[0153] Referring to the communication systems illustrated in Figures 4 and 5, in other words, the embodiments of this application do not limit the relative positional relationship between the computing node and the access network device. The computing node can be a device built into the access network device or a device external to the access network device.

[0154] It should be noted that when the access network equipment adopts a separate architecture of centralized unit (CU) and distributed unit (DU), the computing nodes can be deployed or integrated on the CU or DU, and this application does not limit the specifics.

[0155] The technical solution of this application can be applied to cellular communication systems related to the 3rd Generation Partnership Project (3GPP). For example, 4th generation (4G) communication systems, 5th generation (5G) communication systems, and future communication systems beyond 5th generation. For instance, 4th generation communication systems may include Long Term Evolution (LTE) communication systems, LTE Frequency Division Duplex (FDD) systems, or LTE Time Division Duplex (TDD) systems. 5th generation communication systems may include New Radio (NR) communication systems. The technical solution of this application can also be applied to Wireless Fidelity (WiFi) systems, communication systems supporting the convergence of multiple wireless technologies, device-to-device (D2D) systems, Internet of Things (IoT) communication systems, Industrial Internet (IIoT) communication systems, Vehicle-to-Everything (V2X) communication systems, or satellite communication systems, etc.

[0156] The following describes the terminal equipment, access network equipment, and computing nodes involved in this application.

[0157] Terminal equipment, also known as user equipment (UE), mobile station (MS), mobile terminal (MT), customer premises equipment (CPE), etc., refers to devices that include wireless communication capabilities (providing voice / data connectivity to users). Examples include handheld devices with wireless connectivity, in-vehicle devices, and machine-type communication (MTC) terminals. Currently, terminal equipment can include: mobile phones, tablets, laptops, PDAs, mobile internet devices (MIDs), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, self-driving, remote medical surgery, smart grids, transportation safety, smart cities, and smart homes. For example, wireless terminals in autonomous driving can be drones, helicopters, or airplanes. Wireless terminals in vehicle-to-everything (V2X) systems can be in-vehicle equipment, vehicle components, in-vehicle modules, vehicles, or ships. Wireless terminals in industrial control can be cameras, robots, or robotic arms. Wireless terminals in smart homes can be televisions, air conditioners, robot vacuums, speakers, or set-top boxes. Terminal devices can also be transportation vehicles with wireless communication capabilities, communication modules, and roadside units (RSUs) with terminal device functions.

[0158] It should be noted that the terminal device can be a device or apparatus with a chip, or a device or apparatus with integrated circuitry, or a chip, module, or control unit in the device or apparatus shown above; this application does not limit the specifics. For example, the chip can be a chip in the terminal device responsible for communication functions, such as a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) chip or system-in-package (SIP) chip containing a modem core.

[0159] Access network equipment is a device deployed in a radio access network to provide wireless communication functions for terminal devices. Access network equipment may also be referred to as an access network (RAN) entity, access node, network node, network device, or communication device, etc.

[0160] Specifically, access network equipment can be access network equipment for cellular systems related to the 3rd Generation Partnership Project (3GPP). For example, fourth-generation (4G) mobile communication systems, 5G mobile communication systems, or future mobile communication systems. Access network equipment can also be access network equipment in open RAN (O-RAN or ORAN) or cloud radio access network (CRAN). Alternatively, access network equipment can also be access network equipment in a communication system resulting from the integration of two or more of the above communication systems.

[0161] Access network equipment includes, but is not limited to, one or more of the following: evolved Node B (eNB), radio network controller (RNC), Node B (NB), base station controller (BSC), base transceiver station (BTS), home base station (e.g., home evolved NodeB, or home Node B, HNB), baseband unit (BBU), access point (AP) in a wireless fidelity (WIFI) system, macro base station, micro base station, wireless relay node, donor node, radio controller in a CRAN scenario, wireless backhaul node, transmission point (TP), or transmission and receiving point (TRP). Access network equipment can also be access network equipment in 5G mobile communication systems. For example, next-generation Node B (gNB), TRP, TP in a new radio (NR) system, or one or more antenna panels (including multiple antenna panels) of a base station in a 5G mobile communication system. Alternatively, access network equipment can also be network nodes constituting a gNB or transmission point. Examples include centralized 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 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). Alternatively, access network equipment can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in V2X technology, access network equipment can be roadside units (RSUs).

[0162] It should be noted that CU (or CU-CP and CU-UP), DU, or RU may have different names in different systems, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open centralized unit (O-CU) or an open CU, DU can also be called an open distributed unit (O-DU), centralized unit control plane (CU-CP) can also be called an open centralized unit control plane (O-CU-CP) or an open CU-CP, centralized unit user plane (CU-UP) can also be called an open centralized unit user plane (O-CU-UP) or an open CU-UP, and RU can also be called an open radio unit (O-RU). This application does not impose any specific limitations. Any of the units CU, 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.

[0163] Optionally, for network elements in the ORAN system, each network element can implement the protocol layer functions shown in Table 1 below.

[0164] Table 1

[0165] It should be noted that the access network equipment can be one or more network elements shown in Table 1 above, and this application does not limit the specific network elements.

[0166] It should be noted that Table 1 above is merely an example. In practical applications, the protocol layer functions supported by each network element are not limited. For example, each network element can support more protocol layer functions, or the specific protocol layer functions supported by each network element can be configured according to actual needs. This application does not impose any specific limitations.

[0167] The architecture of the CU and DU of the access network equipment is described below. An access network equipment includes at least one CU and at least one DU. Optionally, the access network equipment may also include at least one RU.

[0168] The following description uses an access network device consisting of one CU and one DU as an example. The CU has some core network functions and may include CU-CP and CU-UP. The CU and DU can be configured according to the protocol layer functions of the wireless network they implement. For example, the CU may be configured to implement the functions of the PDCP layer and above (e.g., RRC layer and / or SDAP layer). The DU may be configured to implement the functions of the protocol layers below the PDCP layer (e.g., RLC layer, MAC layer, and / or PHY layer). Alternatively, the CU may be configured to implement the functions of the PDCP layer and above (e.g., RRC layer and / or SDAP layer), and the DU may be configured to implement the functions of the PDCP layer and below (e.g., RLC layer, MAC layer, and / or PHY layer).

[0169] When a CU includes CU-CP and CU-UP, CU-CP is used to implement the control plane functions of the CU, and CU-UP is used to implement the user plane functions of the CU. For example, when a CU is configured to implement the functions of the PDCP layer, RRC layer, and SDAP layer, CU-CP is used to implement the RRC layer functions and the control plane functions of the PDCP layer, and CU-UP is used to implement the SDAP layer functions and the user plane functions of the PDCP layer.

[0170] The CU-CP can interact with network elements in the core network used to implement control plane functions. These control plane elements can be access and mobility function (AMF) elements, such as the AMF in a 5G mobile communication system. The AMF is responsible for mobility management in the mobile network, such as terminal device location updates, terminal device registration with the network, and terminal device handover. The CU-UP can interact with network elements in the core network used to implement user plane functions. These user plane elements, such as the user plane function (UPF) in a 5G mobile communication system, are responsible for data forwarding and receiving in terminal devices.

[0171] The above CU and DU configurations are merely examples; the functions of the CU and DU can be configured as needed. For instance, the CU or DU can be configured to have more protocol layer functions, or only some protocol layer processing functions. For example, some RLC layer functions and protocol layer functions above the RLC layer can be placed in the CU, while the remaining RLC layer functions and protocol layer functions below the RLC layer can be placed in the DU. Furthermore, the functions of the CU or DU can be divided according to service type or other system requirements. For example, based on latency, functions that require low latency can be placed in the DU, while functions that do not require low latency can be placed in the CU.

[0172] DU and RU can cooperate to implement the functions of the PHY layer. A DU can be connected to one or more RUs. The functions of DU and RU can be configured in various ways depending on the design. For example, a DU can be configured to implement baseband functions, and an RU can be configured to implement mid-RF functions. Another example is that a DU can be configured to implement higher-level functions in the PHY layer, and an RU can be configured to implement lower-level functions in the PHY layer, or to implement both lower-level and RF functions. Higher-level functions in the physical layer can include a portion of the physical layer's functions that are closer to the MAC layer, while lower-level functions in the physical layer can include another portion of the physical layer's functions that are closer to the mid-RF side.

[0173] It should be noted that the access network device can be the device or apparatus shown above, or a component (e.g., a chip), module, or unit in the device or apparatus shown above; this application does not limit the specifics.

[0174] Optionally, the ORAN architecture also involves a RAN Intelligent Controller (RIC) module. Figure 6 illustrates the application architecture of the RIC module within the ORAN architecture. As shown in Figure 6, the communication system includes an RIC module, specifically divided into near-real-time (near-RT) RIC and non-real-time (non-RT) RIC modules. The near-real-time RIC module is used for model training and inference. For example, it trains an artificial intelligence (AI) model and uses this AI model for inference. The near-real-time RIC module can also obtain information for training or inferring the AI ​​model from access network nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU), and from terminal devices. Optionally, the near-real-time RIC module can transmit the results of training or inferring the AI ​​model to access network nodes and / or terminal devices. Optionally, the CU, DU, and RU can exchange these results. For example, the near real-time RIC transmits the results to the DU, which then sends the results to the RU, thereby enabling near real-time intelligent management of the access network.

[0175] The non-real-time RIC module is used for AI model training and inference. For example, it's used to train AI models and then perform inference using those models. The non-real-time RIC module can acquire data from access network nodes (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or terminal devices, and use this data as training or inference data to train or infer AI models, obtaining the corresponding results. The non-real-time RIC module then transmits the results to the access network nodes and / or terminal devices. Optionally, the CU, DU, and RU can exchange these results. For example, the non-real-time RIC module passes the results to the DU, which then sends the results to the RU.

[0176] It should be understood that near real-time RIC modules and non-real-time RIC modules can be deployed separately as independent network elements, or as part of other network devices. For example, near real-time RIC modules can be deployed in access network nodes. For example, near real-time RIC modules can be deployed in CUs and DUs, while non-near real-time RIC modules can be deployed in operations, administration and maintenance (OAM), cloud servers, core network devices, or other network devices.

[0177] The following is a structural diagram of an access network device including a CU and a DU. Figure 7 is a structural diagram of an access network device according to an embodiment of this application. Taking the access network device as a gNB as an example, please refer to Figure 7. In a 5G communication system, gNBs are connected to each other via the Xn interface, and gNBs are connected to the 5th generation mobile communication technology core (5GC) via the NG interface. As shown in Figure 7, gNB1 and gNB2 are connected via the Xn interface. gNB1 is connected to the 5GC via NG interface 1, and gNB2 is connected to the 5GC via NG interface 2.

[0178] A gNB can include a CU and a DU. This means the base station's functions are segmented; some functions are deployed in a gNB-CU, and the remaining functions are deployed in a gNB-DU. Multiple gNB-DUs share a single gNB-CU, which saves costs and facilitates network expansion. For example, as shown in Figure 7, gNB1 includes gNB-CU1, gNB-DU1, and gNB-DU2. gNB-CU1 is connected to gNB-DU1 via F1 interface 1, and to gNB-DU2 via F1 interface 2. The structure of gNB2 is similar to that of gNB1, and will not be described in detail here.

[0179] Figure 7 above is just an example. One gNB-CU can connect to one or more gNB-DUs. This application does not limit the specifics.

[0180] The gNB-CU and gNB-DU can be segmented according to the protocol stack. For example, the protocol stacks corresponding to the RRC layer, SDAP layer, and PDCP layer can be deployed on the gNB-CU. The protocol stacks corresponding to the radio link control (RLC) layer, MAC layer, and PHY layer can be deployed on the gNB-DU. The gNB-CU and gNB-DU are connected via the F1 interface. The above example is only for illustrating gNB-CU and gNB-DU, and this application does not limit the protocol stacks deployed on gNB-CU and gNB-DU.

[0181] In this application, in the scheme of using CU and DU structure for access network equipment as described below, gNB-CU is abbreviated as CU and gNB-DU is abbreviated as DU.

[0182] It should be noted that CU and DU are one way of dividing access network equipment into network units. The functions included in CU and DU can be divided according to evolution or needs, and this application does not limit the functions included in CU and DU respectively. This application also does not limit the names corresponding to CU and DU respectively.

[0183] Compute nodes:

[0184] The computing node can be a component of the access network device (e.g., a processor, circuit, chip, or chip system), or it can be executed by a logic module or software within the access network device (e.g., a computing module). The computing node can also be an external computing power board or service board connected to the access network device. Furthermore, the computing node can be a computing device, terminal device, IoT device, smart home device, industrial control device, vehicle device, or drone device, or any other device that can establish a connection with the access network device.

[0185] The aforementioned computing nodes can be directly connected to access network devices, or they can be connected to access network devices through other links or bearer networks. This application embodiment does not impose any restrictions on this. Access network devices can discover computing nodes in various ways, such as: computing nodes actively registering with access network devices, computing nodes registering with computing node management functions, computing node management functions configuring computing nodes with access network devices, or core network devices configuring computing nodes with access network devices. This application embodiment does not impose any restrictions on this.

[0186] Next, please refer to Figure 8, which is a schematic diagram of a communication scenario involved in an embodiment of this application. The communication scenario illustrated in Figure 8 includes at least one first access network device and N second access network devices, where N is a positive integer greater than or equal to 1. The second access network devices refer to other access network devices that are geographically close to or adjacent to the first access network device within the same geographical area.

[0187] It should be noted that the method executed by the first access network device or the second access network device (or the target access network device) in the embodiments of this application may be executed by the access network device itself, or by some components (such as processors, circuits, chips, or chip systems) in the access network device, or by a logic module or software that implements all or part of the functions of the access network device. For example, the method executed by the first access network device may be executed by the CU of the first access network device, and the method executed by the second access network device may be executed by the CU of the second access network device.

[0188] Taking the scenario illustrated in Figure 8 as an example, this application presents a communication method according to an embodiment. Please refer to Figure 9, which is a flowchart illustrating an embodiment of the communication method in this application. The communication method proposed in this application includes:

[0189] S1. The first access network device sends a first request to the second access network device. The first request includes the calculation information of the first access network device.

[0190] In step S1, the first access network device sends a first request to the second access network device. The first request includes the computing information of the first access network device, which indicates the computing capabilities supported by the first access network device.

[0191] First, we will introduce how the first access network device determines which access network devices will serve as the second access network device.

[0192] In one possible implementation, the first access network device may send a first request to some access network devices. For example, the first access network device sends the first request to some nearby access network devices, and these access network devices that receive the first request act as second access network devices. Another example is that the first access network device pre-configures some access network devices as second access network devices, and then the first access network device sends the first request to these second access network devices.

[0193] In another possible implementation, the first access network device interacts with all its neighboring access network devices (i.e., the second access network devices) to calculate information. Specifically, the first access network device sends a first request to one or more second access network devices in a broadcast manner. For example, the first access network device sends the first request to other surrounding access network devices, and the access network devices that receive the first request become the second access network devices.

[0194] Secondly, it introduces how the first access network device and the second access network device exchange their respective computing information.

[0195] In one possible implementation, the first request is used to request the exchange of configuration data between the first access network device and the second access network device, the configuration data including: calculation information of the first access network device and / or calculation information of the second access network device.

[0196] In another possible implementation, the first request is used to request the exchange of application-level configuration data required for correct interoperability between the first access network device and the second access network device on the Xn-C interface. This application-level configuration data includes computational information of the first access network device and / or the second access network device. For example, the first request and the first response belong to the Xn Setup procedure, the purpose of which is to exchange application-level configuration data needed for two NG-RAN (New Radio Access Network, such as the first and second access network devices) nodes to interoperate correctly over the Xn-C interface.

[0197] In one example, the first request could be an Xn setup request message, and correspondingly, the first response could be an Xn setup response message.

[0198] One example scenario is as follows: During the deployment of a first access network device, the first access network device initiates a connection with its neighboring site (i.e., a second access network device). During this connection initialization process, the first access network device sends a first request to the second access network device to exchange their respective computing information.

[0199] Optionally, when the computing power of the first access network device changes (or is updated), the first access network device may also notify the second access network device of the updated computing information, which indicates the updated computing power supported by the first access network device.

[0200] In one example, the first request could be a configuration update message, such as an NG-RAN node configuration update message.

[0201] It should be noted that the embodiments of this application do not limit the messages carried by the first request and / or the first response.

[0202] Optionally, the first access network device may also periodically send a first request to achieve periodic exchange of computing information between access network devices.

[0203] Optionally, the first access network device may also send a first request to the second access network device based on the request from the second access network device.

[0204] Optionally, the first access network device may also send a first request to the second access network device based on a request from the terminal device. For example, when the terminal device requests a handover, the first access network device sends a first request to the second access network device.

[0205] Optionally, the first access network device may also send a first request to the second access network device based on an event, which includes, but is not limited to, one or more of the following: when the computing power or memory utilization rate of the access network device (or computing node) is lower or higher than a certain threshold, the number of tasks of the access network device (or computing node), or the number of users of the access network device (or computing node) is lower or higher than a certain threshold.

[0206] It should be noted that the first access network device and the second access network device can also exchange their respective computing information in other ways, and this application embodiment does not limit this.

[0207] Next, the specific content of the computational information of the first access network device is described. The computational information of the first access network device includes any one or more of the following:

[0208] Information 1: Identification information of the computing node associated with the first access network device;

[0209] Information 2: First indication information of the first access network device;

[0210] Information 3: Computing resource information of the first access network device;

[0211] Information 4: Computational load information of the first access network device;

[0212] Alternatively, Information 5: Information on computing tasks supported by the first access network device.

[0213] The following sections will introduce information 1 through information 5.

[0214] Optionally, since the first access network device can manage one or more cells, and different cells may provide different computing services, the computing information of the first access network device can be at the access network device level or at the cell level. When the computing information is at the cell level, the computing information of the first access network device may further include: identification information of one or more cells managed by the first access network device.

[0215] Information 1:

[0216] The computing node associated with the first access network device refers to a computing node that can provide computing services to the first access network device. This computing node can be located within the first access network device, for example, it can be a computing node inside the first access network device; alternatively, it can be located outside the first access network device, for example, it can be a computing node connected externally to the first access network device.

[0217] Optionally, the computing nodes associated with the first access network device can also be virtualized computing nodes within the first access network device. The first access network device divides its available computing resources into one or more virtualized computing nodes, and the computing resources used by each virtualized computing node are independent and do not affect each other. For example, each virtualized computing node occupies independent storage and processing resources.

[0218] The computing service in this application embodiment refers to the computing service provided for the application service, which includes, but is not limited to, one or more of the following: video decoding service, image processing service, image recognition service, speech recognition service, machine translation service, gesture recognition service, autonomous driving service, route planning service, neural network model inference service, or neural network model training service, etc.

[0219] For example, the identification information of the computing node associated with the first access network device can be the identifier (ID) of the computing node. For instance, when the computing node is a TEF, the identification information of the computing node can be the TEF ID. The identification information of the computing node can also be the IP address of the computing node, or the media access control (MAC) address of the computing node. This application embodiment does not limit this.

[0220] In one example, the computing nodes associated with the first access network device are shown in Table 2.

[0221] Table 2

[0222] Optionally, the identification information of the computing node associated with the first access network device may also be: the identification information of the computing nodes associated with one or more cells managed by the first access network device. In other words, the identification information of the computing node associated with the first access network device is specifically used to indicate the computing nodes associated with one or more cells managed by the first access network device.

[0223] In one example, the computing nodes associated with the first access network device are shown in Table 3.

[0224] Table 3

[0225] Referring to the examples in Table 3, Cell#1 and Cell#2 managed by the first access network device (RAN#1) can share the same computing node. For example, the computing nodes providing computing services for Cell#1 include: TEF1 (corresponding identification information is TEF ID#1) and TEF2 (corresponding identification information is TEF ID#2). The computing nodes providing computing services for Cell#2 include: TEF1 (corresponding identification information is TEF ID#1), TEF2 (corresponding identification information is TEF ID#2), TEF3 (corresponding identification information is TEF ID#3), and TEF4 (corresponding identification information is TEF ID#4). Cell#3 managed by the first access network device is associated with computing node TEF5 (corresponding identification information is TEF ID#5). Cell#4 managed by the first access network device does not support providing computing services and is not associated with any computing node.

[0226] Information 2:

[0227] The first indication information of the first access network device is used to indicate whether the first access network device supports providing computing services. For example, when the first access network device supports providing computing services, the first indication information of the first access network device is "1"; when the first access network device does not support providing computing services, the first indication information of the first access network device is "0".

[0228] Optionally, the first indication information of the first access network device is specifically used to indicate whether one or more cells managed by the first access network device support providing computing services.

[0229] In one example, the first indication information of the first access network device is shown in Table 4.

[0230] Table 4

[0231] Referring to the examples in Table 4, the cells managed by the first access network device: Cell#1, Cell#2 and Cell#3 support providing computing services, while the cell managed by the first access network device: Cell#4 does not support providing computing services.

[0232] Information 3:

[0233] The computing resource information of the first access network device indicates the computing resources related to the computing service. This computing resource information includes any one or more of the following: hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information.

[0234] The hardware resource information of the first access network device indicates the hardware resources of the computing node associated with the first access network device. For example, the hardware resources include, but are not limited to, one or more of the following: the central processing unit (CPU) of the computing node, the application processor (AP) of the computing node, the graphics processing unit (GPU) of the computing node, the image signal processor (ISP) of the computing node, the video codec of the computing node, the digital signal processor (DSP) of the computing node, and / or, the neural network processing unit (NPU) of the computing node, etc. As another example, the hardware resource information indicates the model of the hardware device of the computing node.

[0235] Processing capacity information can indicate the floating-point arithmetic capability of a computing node. It can also indicate the average processing latency of a computing node for processing computational tasks. Average processing latency can be the processing latency of a single computational task, the average processing latency of all computational tasks, or the average processing latency of a specific type of computational task. Examples include the average processing latency for image processing tasks, the average processing latency for image recognition tasks, the average processing latency for gesture recognition tasks, or the average processing latency for neural network model training tasks.

[0236] Storage capacity information indicates the amount of storage space available to the compute node. For multiple compute nodes, each compute node can be configured with dedicated storage space, or multiple compute nodes can be configured with shared storage space. Therefore, the storage capacity information can indicate the size of the compute node's dedicated storage space or the size of its shared storage space. For example, the storage capacity information indicates the total storage capacity of the compute node, and / or the amount of storage space available to the compute node.

[0237] The transmission resource information indicates the total transmission bandwidth of the computing node, and / or the available transmission bandwidth of the computing node.

[0238] Software resource information can indicate the various types of software, computing services, computing tasks, application services, artificial intelligence (AI) algorithms, or neural network models that the computing node supports running (or processing, or executing). For example: when the computing service supported by the computing node is gesture recognition, the software resources supported by the computing node may include recurrent neural networks (RNNs); when the computing service supported by the computing node is image processing, the software resources supported by the computing node may include convolutional neural networks (CNNs) and generative adversarial networks (GANs); when the computing service supported by the computing node is video decoding, the software resources supported by the computing node may include video encoding algorithms, such as the high-efficiency video coding (H.265-HEVC) algorithm; when the computing service supported by the computing node is route planning, the software resources supported by the computing node may include the shortest path algorithm (Dijkstra's algorithm), etc. The software may also include the operating system that the computing node supports running.

[0239] Optionally, the computing resource information may also indicate the relevant computing resources for computing services provided by one or more cells managed by the first access network device.

[0240] Information 4:

[0241] The computing load information of the first access network device indicates the load status of the computing resources provided by the first access network device. The computing load information includes any one or more of the following: processing resource load information, storage resource load information, or transmission resource load information. For example, the computing load information indicates the memory utilization rate, transmission bandwidth utilization rate, and / or processing resource utilization rate of the computing node.

[0242] Optionally, the computing load information may also indicate the load status of computing resources provided by one or more cells managed by the first access network device.

[0243] In one example, the calculation information of the first access network device is shown in Table 5.

[0244] Table 5

[0245] In another example, the computing load information of the first access network device indicates the number of computing tasks or users that the first access network device can support. The number of computing tasks or users that can be supported characterizes the computing capacity of the first access network device (or the computing nodes associated with the first access network device).

[0246] Information 5:

[0247] The computing task information supported by the first access network device is used to indicate the computing tasks supported by the first access network device, the services supported by the first access network device, the applications supported by the first access network device, and / or the computing service information provided by the first access network device. The computing tasks supported by the first access network device refer to the computing tasks that the first access network device can process. The services supported by the first access network device refer to the services that the first access network device can process or the computing tasks related to those services.

[0248] For example, the computing task information supported by the first access network device includes: the application types supported by the first access network device, such as the application name, domain name, or identifier.

[0249] Furthermore, the supported service types include, but are not limited to, one or more of the following: video decoding services, image rendering services, image processing services, image recognition services, speech recognition services, machine translation services, gesture recognition services, autonomous driving services, route planning services, neural network model inference services, or neural network model training services, etc.

[0250] In another example, for large AI model businesses, the supported models or types include generative pre-trained (GPT) models.

[0251] For example, the computing task information supported by the first access network device also includes: Quality of Service (QoS) information for the computing task supported by the first access network device. This QoS information indicates the quality of service that the first access network device can achieve when performing the computing task. For example, the processing latency when the first access network device performs the computing task. The aforementioned QoS information can also be related to specific computing services. For example, when the computing service is an image rendering service, the QoS information may also include the image resolution, image bitrate, or image sharpness. For another example, when the computing service is a neural network model inference service, the QoS information may also include the prediction accuracy.

[0252] In another instance, the computing task information supported by the first access network device may also include the identification information of the computing task. For example, the task ID.

[0253] For example, the task ID can be a set of serial numbers or a set of strings. The task ID can be pre-configured by the core network device or the computing node management function, or it can be negotiated and agreed upon between computing nodes, or it can be customized by the computing node or the access network device. This application embodiment does not limit this.

[0254] The identification information for this computing task can be pre-defined. For example, it can be pre-configured for computing nodes or access network devices, allowing different access network devices or computing nodes to identify the corresponding computing task based on this identification information. For instance, the identification information for computing tasks related to video applications is set to "video", the identification information for computing tasks related to extended reality (XR) applications is set to "XR", and the identification information for computing tasks related to AI applications is set to "AI".

[0255] The identification information for this computing task can also be the identification information assigned to each computing task by the computing node management function. For example, the identification information for computing tasks related to video applications is set to "Task ID#1", the identification information for computing tasks related to extended reality (XR) applications is set to "Task ID#2", and the identification information for computing tasks related to AI applications is set to "Task ID#3".

[0256] The identification information for this computing task can also be custom identification information defined by the access network device or the computing node. In another example, the computing information of the first access network device is shown in Table 6.

[0257] Table 6

[0258] S2. The second access network device sends a first response to the first access network device according to the first request. The first response includes the calculation information of the second access network device.

[0259] In step S2, the first response is the response to the first request.

[0260] In one example, the first request could be an Xn setup request message, and correspondingly, the first response could be an Xn setup response message.

[0261] In another example, the first request could be a configuration update message, such as an NG-RAN node configuration update message. Correspondingly, the first response could be an NG-RAN NODE CONFIGURATION UPDATE ACKNOWLEDGE.

[0262] The computing information of the second access network device is similar to that of the first access network device. The computing information of the second access network device includes any one or more of the following: the identification information of the computing node associated with the second access network device, the first indication information of the second access network device, the computing resource information of the second access network device, or the computing load information of the second access network device.

[0263] Optionally, since the second access network device also manages one or more cells, and different cells may provide different computing services, the computing information of the second access network device can be at the access network device level or at the cell level. When the computing information is at the cell level, the computing information of the second access network device may also include: identification information of one or more cells managed by the second access network device.

[0264] For example, the identification information of the computing node associated with the second access network device is specifically used to indicate the computing node associated with one or more cells managed by the second access network device; the first indication information of the second access network device is specifically used to indicate whether one or more cells managed by the second access network device support providing computing services; the computing resource information of the second access network device is specifically used to indicate the relevant computing resources for providing computing services in one or more cells managed by the second access network device; and / or, the computing load information of the second access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the second access network device.

[0265] The calculation information for the second access network device is similar to that for the first access network device in step S1 above, and will not be repeated here.

[0266] Optionally, the scheme described in steps S1 to S2 above can also be implemented by a third party. For example, the first access network device sends computing information to a computing node management function (such as the AMF or SMF of the core network device, or a server). The computing node management function forwards the first request to the second access network device based on the computing information. The computing node management function receives a first response from the second access network device and obtains the computing information of the second access network device based on the first response. Alternatively, the computing node management function obtains its respective computing information from both the first and second access network devices.

[0267] Optionally, when a terminal device managed by the first access network device needs to switch, the first access network device can also obtain computing information related to other access network devices from the computing node management function. The first access network device determines the target access network device based on this computing information.

[0268] Optionally, in this application, when the access network device adopts a separate architecture of CU and DU, in step S1 above, the CU of the first access network device generates a first request, and then the CU of the first access network device sends the first request to the second access network device through the DU or RU of the first access network device. In step S2 above, the CU of the second access network device receives the first request through the DU or RU of the second access network device, and then the CU of the second access network device generates a first response based on the first request. The CU of the second access network device sends the first response to the first access network device through the DU or RU of the second access network device.

[0269] In this embodiment, the first access network device and the second access network device can exchange their respective computing information, which indicates the computing services supported (or provided) by the access network devices. The first access network device can select a suitable target access network device to execute the computing task based on the computing information of the second access network device. For example, during the process of a terminal device switching from the first access network device to another access network device, if the terminal device needs computing services from an access network device, the first access network device can select a suitable target access network device for the terminal device based on the computing information of the second access network device. The target access network device belongs to the second access network device. This ensures that after the terminal device switches to the target access network device, the target access network device can provide computing services to the terminal device, ensuring that the computing tasks required by the terminal device can be successfully executed, guaranteeing that the computing tasks requested by the terminal device are not interrupted during the switching process, ensuring the service continuity of the terminal device, and improving the user experience. In addition, the computing information exchanged between the first and second access network devices can also have other uses. For example, after the first and second access network devices exchange computing information, the current network can be analyzed and processed based on the computing information of multiple access network devices. For example, after the first access network device and the second access network device exchange computational information, the computational task can be distributed among multiple access network devices based on their computational information, allowing for distributed processing. For instance, if the computational task is to train a neural network model, then multiple access network devices can perform federated learning on that neural network model.

[0270] Based on the aforementioned embodiments, the following describes how the computing tasks of the terminal device are switched between the first access network device and the target access network device. Specifically, there are two possible implementation methods: Implementation Method 1: The target access network device is determined on the access network device side; Implementation Method 2: The target access network device is determined on the core network device side. These will be described separately below.

[0271] Implementation Method 1: The target access network device is determined on the access network device side. Please refer to Figure 10a, which is a schematic flowchart of another embodiment of the communication method in this application. The communication method proposed in this application includes:

[0272] D1. Report the measurement results of the terminal equipment.

[0273] In step D1, the terminal device may report the measurement results of the terminal device to the first access network device. The measurement results include, but are not limited to, one or more of the following: reference signal received power (RSRP), reference signal received quality (RSRQ), and / or channel state information (CSI).

[0274] It should be noted that step D1 is an optional step.

[0275] If step D1 is not executed, the first access network device may trigger step D2 on its own. This self-triggering may be due to the first access network device determining that it does not support the computing task of the terminal device, and therefore triggering step D2. For example, if the computing power of the first access network device cannot meet the computing requirements of the terminal device's computing task, the first access network device may trigger the determination of a target access network device so that the target access network device can perform the computing task of the terminal device.

[0276] When step D1 is executed, for example, if the terminal device needs to switch from the first access network device to the next access network device, the terminal device reports its measurement results to the first access network device. These measurement results include the terminal device's measurement results of neighboring cells.

[0277] D2. Identify the target access network equipment.

[0278] The target access network device can be determined in two ways, which will be explained below.

[0279] Method 1:

[0280] Before step D2, steps S1 and S2 are executed, therefore, the first access network device has acquired the computational information of one or more second access network devices. Then, based on the measurement results of the terminal device and the computational information of one or more second access network devices, the first access network device determines the target access network device, which supports providing communication and computing services to the terminal device, and the target access network device belongs to the one or more second access network devices.

[0281] The target access network device supporting the provision of communication and computing services to the terminal device can also be replaced by: the target access network device being an access network device that supports executing the computing tasks requested by the terminal device; or the computing resources (or computing services) provided by the target access network device being able to execute the computing tasks requested by the terminal device; or the computing nodes associated with the target access network device being able to execute the computing tasks requested by the terminal device; or the target access network device being able to meet the computing capacity (or computing resources, or computing services, or quality of service) requirements of the terminal device when requesting to execute the computing task.

[0282] In one possible implementation, a first access network device determines a first set based on the measurement results of the terminal device. The first set includes one or more access network devices, and the access network devices included in the first set are those with better signal quality among the one or more second access network devices. Then, the first access network device determines a target access network device based on the calculation information of each access network device included in the first set. The target access network device is the access network device in the first set that supports providing computing services to the terminal device.

[0283] In another possible implementation, the first access network device determines a second set based on computational information from one or more second access network devices. The second set includes access network devices among the one or more second access network devices that support providing computing services to the terminal device. Then, based on the measurement results of the terminal device, the first access network device determines a target access network device from the second set, which is an access network device in the second set with better signal quality.

[0284] Optionally, the first access network device may also obtain computing requirement information of the terminal device, which indicates information about the computing tasks that the terminal device needs to perform, or the computing requirement information indicates the computing power requirements of the computing tasks that the terminal device supports performing. Based on the computing requirement information of the terminal device and the computing information of one or more second access network devices, the first access network device determines a target access network device that meets the computing requirements of the terminal device.

[0285] In one example, the first access network device can obtain the computing requirement information locally. For instance, if the first access network device is processing a computing task for the terminal device and the computing task needs to be switched to the target access network device for continued execution, the first access network device determines the computing requirement information based on the context information of the computing task.

[0286] In another example, the first access network device can obtain the computing requirement information from the computing node management function.

[0287] In another example, the terminal device can proactively report the computing requirement information to the first access network device. For instance, in step D1, the terminal device can also report the computing requirement information to the first access network device.

[0288] In another possible implementation, the first access network device determines a third set based on computational information from one or more second access network devices. This third set includes one or more cells that support the terminal device in completing its computational tasks, and these cells are managed by the one or more second access network devices. Then, based on the measurement results from the terminal device, the first access network device determines a fourth set from the third set. This fourth set includes candidate target cells, which are cells with better signal quality from the third set. The access network device managing these candidate target cells is designated as the target access network device.

[0289] Optionally, if the first access network device already provides computing services to the terminal device, and the terminal device already has computing tasks being executed by the first access network device, then the first access network device can determine the target access network device based on the context information of the computing task. This ensures that the computing service requested by the terminal device can be executed by the target access network device, improving the handover success rate.

[0290] Optionally, the first access network device may also request the terminal device to report the context information of the computing task, which is the computing task requested by the terminal device. Then, based on the context information of the computing task, the first access network device determines a target access network device that supports the execution of the computing task. This ensures that the computing service requested by the terminal device can be executed by the target access network device, improving the handover success rate.

[0291] For contextual information regarding the computational task, please refer to the subsequent embodiments; it will not be repeated here.

[0292] In step D2, the first access network device can further determine candidate target cells. The candidate target cells refer to the cells that the terminal device needs to access during the handover process. The candidate target cells support providing communication services and computing services to the terminal device.

[0293] The candidate target cell supporting the provision of communication and computing services to the terminal device can also be replaced by: the candidate target cell being an access network device that supports executing the computing tasks requested by the terminal device; or the computing resources (or computing services) provided by the candidate target cell being able to execute the computing tasks requested by the terminal device; or the computing nodes associated with the candidate target cell being able to execute the computing tasks requested by the terminal device; or the candidate target cell being able to meet the computing capacity (or computing resources, or computing services, or quality of service) requirements of the terminal device when requesting to execute the computing task.

[0294] In one example, the computation information of the second access network device includes first indication information, which indicates whether the second access network device supports providing computation services. Based on the computation information of one or more second access network devices, the first access network device determines candidate target cells, which need to support providing computation services.

[0295] In another example, the computation information of the second access network device includes computation load information, which indicates the remaining available computation resources of the second access network device. Based on the computation information of one or more second access network devices, the first access network device determines candidate target cells whose remaining available computation resources satisfy the computational requirements of the terminal device.

[0296] In another example, the computing information of the second access network device includes computing resource information, which indicates the computing resources related to the computing services provided by the second access network device. Taking the computing resource information indicating the computing tasks supported by the second access network device as an example, based on the computing information of one or more second access network devices, the first access network device determines candidate target cells, and the computing task requested by the terminal device belongs to the computing tasks supported by the candidate target cell.

[0297] In another example, the computation information of the second access network device includes computation task information supported by the second access network device. This computation task information is similar to that of the first access network device, indicating the computation tasks supported by the second access network device, the services supported by the second access network device, the applications supported by the second access network device, and / or the computation service information provided by the second access network device. The first access network device determines candidate target cells based on the computation information of one or more second access network devices (computation task information supported by the second access network devices), and the computation task requested by the terminal device belongs to the computation tasks supported by the candidate target cell. For example, the candidate target cell can meet the QoS requirements for the terminal device to perform the computation task.

[0298] Method 2:

[0299] The first access network device determines the target access network device based on the measurement results reported by the terminal device. This target access network device can be an access network device with good signal quality as indicated by the measurement results. In other words, in Method 2, the first access network device determines the target access network device solely based on the measurement results reported by the terminal device. Whether the target access network device supports executing the terminal device's computational tasks is not considered by the first access network device. The target access network device itself determines whether to allow the terminal device to access the network.

[0300] D3. The first access network device sends a second request to the target access network device. The second request instructs the terminal device to request a handover to the target access network device.

[0301] In step D3, after determining the target access network device, the first access network device sends a second request to the target access network device, which instructs the terminal device to request a handover to the target access network device.

[0302] Optionally, the second request may further include context information of the computing task, which is the computing task requested to be executed by the terminal device. The context information of the computing task includes any one or more of the following: identification information of the computing task, identification information of the application, bearer information of the computing task, identification information of the computing node supporting the execution of the computing task, or, second indication information. The context information of the computing task is described in detail below.

[0303] The identification information for a computing task can be a task identifier (task ID). This identification information can indicate the type of computing task, such as "image encoding / decoding," "video encoding / decoding," "AI model training," "path planning," or "autonomous driving." The target access network device directly or indirectly determines other information about the computing task based on this identification information. For example, the target access network device determines the QoS parameters of the computing task corresponding to the task ID based on the task ID to save communication overhead.

[0304] The application's identification information indicates that the application is related to computing tasks. Examples include video applications, navigation applications, autonomous driving applications, and communication applications. For instance, the application's identification information can be the application's identifier (APP ID), its fully qualified domain name (FQDN), or its name.

[0305] The identification information of the computing nodes that support the execution of computing tasks indicates which computing nodes support the execution of the computing tasks requested by the terminal device. For example, if a first access network device is associated with computing node 1 and computing node 2, and the first access network device determines that computing node 1 supports the execution of the computing service requested by the terminal device, then the second request can carry the identification information of computing node 1. This allows the target access network device to detect whether it has an association with computing node 1, and thus determine whether it can provide computing services to the terminal device through computing node 1. Exemplarily, the identification information of the computing node can be the tunnel endpoint ID (TEID) of the computing node, the IP address of the computing node, or the identifier of the computing node.

[0306] The second instruction information indicates that the computing task needs to be switched to the target access network device for continued execution. In one example, while the computing task is being executed by the first access network device, the terminal device needs to switch to the target access network device, at which point the computing task has not yet been completed. Therefore, the second request sent by the first access network device to the target access network device needs to carry the second instruction information, which instructs the target access network device to continue executing the computing task.

[0307] Optionally, the context information of the computing task may also include: relevant information about the terminal device, such as the identity of the terminal device; and the quality of service (QoS) parameters of the computing task, which indicate the QoS requirements of the computing data related to the computing task.

[0308] Optionally, when the computation task is related to a neural network model, the context information of the computation task may also include any one or more of the following: computational state information of the neural network model related to the computation task, type information of the neural network model, parameter information of the neural network model, key-value store (KV) cache information of the neural network model, information of one or more intermediate layers included in the neural network model, initial input feature information of the neural network model, or output feature information of one or more intermediate layers of the neural network model. These are described below.

[0309] The type information of the neural network model and / or the parameter information of the neural network model, including but not limited to one or more of the following: the architecture type of the neural network model, the activation function of the neural network model, the loss function of the neural network model, the optimizer of the neural network model, the layer type of the neural network model, or the regularization method of the neural network model.

[0310] For example, neural network model architecture types include: feedforward neural networks (FNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), long short-term memory networks (LSTMs), generative adversarial networks (GANs), or generative pre-trained (GPT) models; activation functions of neural network models include: rectified linear unit (ReLU), sigmoid, or hyperbolic tangent function (Tanh); loss functions of neural network models are used to evaluate model performance during training, such as mean squared error (MSE) and cross-entropy; optimizers of neural network models include: stochastic gradient descent (SGD), adaptive moment estimation (Adam), or root mean square propagation (RMSprop). Neural network model layer types include fully connected layers (Dense), convolutional layers, pooling layers, or recurrent layers (such as LSTM, GRU), etc.; neural network model regularization methods include L1 and L2 regularization, Dropout, etc.

[0311] The parameters of a neural network model include, but are not limited to, one or more of the following: weights, biases, learning rate, momentum, decay rate, batch size, or number of iterations. Specifically, weights refer to the weight values ​​of each connection, determining how the input signal affects downstream nodes in the neural network model; biases refer to the bias values ​​of each layer or node in the neural network model, used to adjust the output of the activation function; the learning rate refers to the rate at which weights are adjusted during optimization; momentum refers to the parameter used to accelerate convergence during optimization; the decay rate refers to the rate at which the learning rate decays over time; the batch size refers to the number of samples used in each training iteration; and the number of iterations refers to the number of times the dataset is used to train the model.

[0312] The computational state information of the neural network model can be used to indicate to the terminal device, during handover, that the relevant tasks of the neural network model need to be switched to the target access network device for execution. The computational state information of the neural network model can also indicate that the relevant tasks of the neural network model need to be continued by a new access network device (or a new computing node). Optionally, the computational state information of the neural network model includes any one or more of the following: intermediate features of the neural network model, gradient information of the neural network model, model configuration information of the neural network model, or training progress of the neural network model.

[0313] The intermediate features indicate the intermediate activation values ​​or feature maps generated by the neural network model during training. The gradient information indicates the gradient values ​​calculated by the neural network model during backpropagation. The model configuration information indicates the configuration parameters of the neural network model during training, such as the number of layers and the number of nodes per layer. The training progress of the neural network model indicates the current batch, number of iterations, or degree of completion of the training.

[0314] Information about one or more intermediate layers included in a neural network model is used to indicate the one or more intermediate layers included in the neural network model. These intermediate layers can also be referred to as the split points or breakpoints of the neural network model.

[0315] KV Cache is a method to accelerate large model inference, using key (K) and value (V) representations. The context information for this computational task includes the KV Cache information of the neural network model, which can improve the inference efficiency of the target access network device for that neural network model.

[0316] The initial input feature information of the neural network model, such as the feature information of the terminal device that initially inputs the neural network model.

[0317] The output feature information of one or more intermediate layers of a neural network model, for example, the feature information output by one or more intermediate layers of the neural network model when the first access network device performs the training task of the neural network model.

[0318] The input or output feature information of the neural network model can also be the number of basic data units, such as the number of tokens. The number of tokens refers to the number of basic data units that have been input or output during the inference process of the neural network model.

[0319] For example, the second request could be a "handover request".

[0320] In another example, the second request could be a newly defined message for computing task migration, which is not limited in this embodiment.

[0321] D4. The first access network device receives a second response from the target access network device.

[0322] In step D4, after receiving the second request, the target access network device sends a second response to the first access network device based on the second request. This second response is a response to the second request. The second response indicates that the terminal device successfully switched to the target access network device, or it indicates that the switch failed.

[0323] In one possible implementation, when the second request also includes context information of the computing task, the target access network device determines whether to allow the terminal device to access the network based on the context information of the computing task and the computing information of the target access network device. For example, if the computing node associated with the target access network device supports executing the computing task, the target access network device allows the terminal device to access the network. Conversely, if the computing node associated with the target access network device does not support executing the computing task, or if the computing resources provided by the target access network device are insufficient to execute the computing task, the target access network device does not allow the terminal device to access the network.

[0324] The computing information of the target access network device includes any one or more of the following: identification information of the computing node associated with the target access network device, the computing node being used to provide computing services, first indication information of the target access network device, the first indication information of the target access network device indicating whether the target access network device supports providing computing services, computing resource information of the target access network device, the computing resource information of the target access network device indicating the computing resources related to the computing services, or, computing load information of the target access network device, the computing load information of the target access network device indicating the load status of the computing resources provided by the target access network device.

[0325] Specifically, the computing information of the target access network device also includes: identification information of one or more cells managed by the target access network device; wherein, the first indication information of the target access network device is specifically used to indicate whether one or more cells managed by the target access network device support providing computing services, the computing resource information of the target access network device is specifically used to indicate the relevant computing resources for providing computing services in one or more cells managed by the target access network device, and / or, the computing load information of the target access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the target access network device.

[0326] Similar to the computing information of the first access network device, the computing resource information of the target access network device includes any one or more of the following: hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information. The computing load information of the target access network device includes any one or more of the following: processing resource load information, storage resource load information, or transmission resource load information.

[0327] The calculation information for the target access network device is similar to that for the first access network device mentioned above, and will not be repeated here.

[0328] Optionally, when the target access network device does not allow the terminal device to access, the second response may also indicate the reason why the terminal device failed to switch to the target access network device.

[0329] In one example, the reasons for a handover failure include: the terminal device is not allowed to access the target access network device in this requested handover, or the terminal device is prohibited from accessing the target access network device in this and future requested handovers.

[0330] In another example, the reasons for the handover failure include: the target access network device does not support providing computing services, the target access network device has insufficient computing resources, the target access network device does not support the computing task requested by the terminal device, or the target access network device has no connection with a computing node that supports performing computing tasks.

[0331] The specific reason for the switching failure can be indicated in a variety of ways, including but not limited to one or more of the following: reason value, indication information, field, or flag bit.

[0332] In one example, the reason value "00" indicates that the target access network device does not support providing computing services, the reason value "01" indicates that the target access network device has insufficient computing resources, the reason value "10" indicates that the target access network device does not support the computing task requested by the terminal device, and the reason value "11" indicates that the target access network device has no connection with the computing node that supports performing the computing task.

[0333] In another example, the field indicating the reason is "Computing not supported", "not supported", or "not available", indicating that the target access network device does not support providing computing services. The field indicating the reason is "Insufficient computing resources" or "temporarily not available", indicating that the target access network device has insufficient computing resources.

[0334] In one example scenario, when the terminal device is in the RRC connected state, the second request can be a handover request, and the second response can be a handover request ack or a handover request failure.

[0335] Optionally, in this application, when the access network device adopts a separate architecture of CU and DU, in step D1 above, the DU or RU of the first access network device receives the measurement results reported by the terminal device. In step D2 above, the CU of the first access network device determines the target access network device based on the measurement results of the terminal device and the calculation information of one or more second access network devices. In step D3 above, the CU of the first access network device sends a second request to the target access network device through the DU or RU of the first access network device. In step D4 above, the CU of the target access network device generates a second response based on the second request, and then the CU of the target access network device sends the second response to the first access network device through the DU or RU of the target access network device.

[0336] In this embodiment, when a terminal device needs to switch, the first access network device can select a target access network device for the terminal device based on the computing information of one or more second access network devices. This target access network device supports providing communication and computing services to the terminal device. Alternatively, when a terminal device needs to switch, the second request sent by the first access network device to the target access network device can carry context information of the computing task requested by the terminal device, so that the target access network device can determine whether to allow the terminal device to access based on the context information of the computing task. Through the above technical solutions, after the terminal device switches access network devices, the new access network device can support providing computing services to the terminal device, ensuring that the terminal device can execute computing tasks normally, guaranteeing that the computing tasks requested by the terminal device are not interrupted during the switching process, ensuring the service continuity of the terminal device, and improving the user experience.

[0337] Method 2: The target access network device is determined on the core network equipment side.

[0338] The core network equipment can be: AMF, SMF, or compute node management function, and this application embodiment does not limit this.

[0339] Please refer to Figure 10b, which is a schematic flowchart of another embodiment of the communication method in this application. The communication method proposed in this application includes:

[0340] G1. The first access network device reports its calculation information to the core network device.

[0341] Optionally, the first access network device may also report the context information of the terminal device's computing tasks to the core network device.

[0342] G2, the second access network device reports the calculation information of the second access network device to the core network device.

[0343] G3. Based on the calculation information of the first access network device and the calculation information of the second access network device, the core network device determines the candidate target cell.

[0344] G4. The core network equipment sends candidate target cells to the first access network equipment to assist the first access network equipment in determining the cell to be handed over to the terminal equipment.

[0345] In this embodiment of the application, when the terminal device needs to switch, the core network device can also assist the access network device in determining the candidate target cell, thereby reducing the processing burden of the access network device.

[0346] Next, the communication device involved in the embodiments of this application will be described. This communication device can be used in the first access network device, the second access network device, and / or the target access network device in the foregoing embodiments.

[0347] Figure 11 is a schematic diagram of a communication device according to an embodiment of this application. Referring to Figure 11, the communication device 1100 includes a transceiver module 1101 and a processing module 1102.

[0348] The communication device 1100 includes an access network device, which may be a first access network device, a second access network device, and / or a target access network device. Alternatively, the communication device 1100 includes components (e.g., chips), modules, or units within the access network device, which may be a first access network device, a second access network device, and / or a target access network device.

[0349] The communication device 1100 can be used to perform all or part of the steps performed by the first access network device in the embodiment shown in FIG9, as detailed in the relevant description in the embodiment shown in FIG9 above.

[0350] The communication device 1100 can be used to perform all or part of the steps performed by the second access network device in the embodiment shown in FIG9, as detailed in the relevant description in the embodiment shown in FIG9 above.

[0351] The communication device 1100 can be used to perform all or part of the steps performed by the first access network device in the embodiment shown in FIG10b, as detailed in the relevant description in the embodiment shown in FIG10b above.

[0352] The communication device 1100 can be used to perform all or part of the steps performed by the target access network device in the embodiment shown in FIG10b, as detailed in the relevant description in the embodiment shown in FIG10b above.

[0353] The processing module 1102 is used for data processing. The transceiver module 1101 is used to implement the corresponding communication functions.

[0354] Optionally, the transceiver module 1101 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiments. The receiving module is used to perform the receiving operation in the above method embodiments.

[0355] It should be noted that the communication device 1100 may include a transmitting module but not a receiving module. Alternatively, the communication device 1100 may include a receiving module but not a transmitting module. Specifically, it depends on whether the above-described scheme executed by the communication device 1100 includes both transmitting and receiving actions.

[0356] Optionally, the communication device 1100 may further include a storage module, which can be used to store instructions and / or data. The processing module 1102 can read the instructions and / or data in the storage module so that the communication device 1100 can implement the aforementioned method embodiments.

[0357] The communication device 1100 can be used to perform the actions performed by the first access network device in the embodiment shown in FIG9. The processing module 1102 is used to perform processing-related operations by the first access network device in the embodiment shown in FIG9. The transceiver module 1101 is used to perform receiving or transmitting-related operations by the first access network device in the embodiment shown in FIG9.

[0358] For example, the communication device 1100 is used to execute the following scheme:

[0359] The transceiver module 1101 is used to send a first request, the first request including computing information of the first access network device, the computing information of the first access network device indicating the computing capabilities supported by the first access network device;

[0360] The transceiver module 1101 is also used to receive a first response, which is a response to the first request. The first response includes computing information of the second access network device, which indicates the computing capabilities supported by the second access network device.

[0361] The communication device 1100 can be used to perform the actions performed by the second access network device in the embodiment shown in FIG9. The processing module 1102 is used to perform processing-related operations by the second access network device in the embodiment shown in FIG9. The transceiver module 1101 is used to perform receiving or transmitting-related operations by the second access network device in the embodiment shown in FIG9.

[0362] For example, the communication device 1100 is used to execute the following scheme:

[0363] The transceiver module 1101 is used to receive a first request, the first request including computing information of the first access network device, the computing information of the first access network device indicating the computing capabilities supported by the first access network device;

[0364] The transceiver module 1101 is also used to send a first response, which is a response to the first request. The first response includes computing information of the second access network device, which indicates the computing capabilities supported by the second access network device.

[0365] The communication device 1100 can be used to perform the actions performed by the first access network device in the embodiment shown in FIG10b. The processing module 1102 is used to perform processing-related operations of the first access network device in the embodiment shown in FIG10b. The transceiver module 1101 is used to perform receiving or transmitting-related operations of the first access network device in the embodiment shown in FIG10b.

[0366] For example, the communication device 1100 is used to execute the following scheme:

[0367] The transceiver module 1101 is used to send a second request to the target access network device. The second request instructs the terminal device to request a switch to the target access network device. The second request includes context information of the computing task requested by the terminal device.

[0368] The transceiver module 1101 is used to receive a second response from the target access network device, the second response being a response to the second request.

[0369] The communication device 1100 can be used to perform the actions performed by the target access network device in the embodiment shown in FIG10b. The processing module 1102 is used to perform processing-related operations of the target access network device in the embodiment shown in FIG10b. The transceiver module 1101 is used to perform receiving or transmitting-related operations of the target access network device in the embodiment shown in FIG10b.

[0370] For example, the communication device 1100 is used to execute the following scheme:

[0371] The transceiver module 1101 is configured to receive a second request from a first access network device. The second request instructs a terminal device to request a switch to the target access network device and requests the target access network device to provide computing and communication services to the terminal device. The second request includes context information of the computing task that the terminal device requests to execute.

[0372] The transceiver module 1101 is used to send a second response to the first access network device according to the second request and the computing information of the target access network device, wherein the computing information of the target access network device indicates the computing capabilities supported by the target access network device.

[0373] For other implementation methods, please refer to the relevant descriptions in the embodiments shown in Figures 9 and 10b above, which will not be repeated here.

[0374] In one example, the communication device 1100 is applied to a first access network device, the communication device 1100 comprising:

[0375] The transceiver module 1101 is used to send a first request, the first request including computing information of the first access network device, the computing information of the first access network device indicating the computing capabilities supported by the first access network device;

[0376] The transceiver module 1101 is also used to receive a first response, which is a response to the first request. The first response includes computing information of the second access network device, which indicates the computing capabilities supported by the second access network device.

[0377] In one possible implementation, the first request is used to request the exchange of configuration data between the first access network device and the second access network device, the configuration data including: calculation information of the first access network device and / or calculation information of the second access network device.

[0378] In one possible implementation, the first request is specifically used to request the exchange of application-level configuration data required for proper interoperability between the first access network device and the second access network device on the Xn-C interface. The application-level configuration data includes: computational information of the first access network device and / or computational information of the second access network device.

[0379] In one possible implementation, the computational information of the first access network device includes:

[0380] The identification information of the computing node associated with the first access network device, wherein the computing node is used to provide computing services.

[0381] The first indication information of the first access network device indicates whether the first access network device supports providing computing services.

[0382] The computing resource information of the first access network device indicates the computing resources related to the computing service.

[0383] Alternatively, the computing load information of the first access network device indicates the load status of the computing resources provided by the first access network device.

[0384] The calculation information of the second access network device includes:

[0385] The identification information of the computing node associated with the second access network device, wherein the computing node is used to provide computing services.

[0386] The first indication information of the second access network device indicates whether the second access network device supports providing computing services.

[0387] The computing resource information of the second access network device indicates the computing resources related to the computing service.

[0388] Alternatively, the computing load information of the second access network device indicates the load status of the computing resources provided by the second access network device.

[0389] In one possible implementation, the computational information of the first access network device further includes:

[0390] Identification information of one or more cells managed by the first access network device;

[0391] Specifically, the identification information of the computing nodes associated with the first access network device is used to indicate the computing nodes associated with one or more cells managed by the first access network device.

[0392] The first indication information of the first access network device is specifically used to indicate whether one or more cells managed by the first access network device support providing computing services.

[0393] The computing resource information of the first access network device is specifically used to indicate the relevant computing resources for one or more cells managed by the first access network device to provide the computing service.

[0394] And / or, the computing load information of the first access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the first access network device;

[0395] The calculation information of the second access network device also includes:

[0396] Identification information of one or more cells managed by the second access network device;

[0397] Specifically, the identification information of the computing node associated with the second access network device is used to indicate the computing nodes associated with one or more cells managed by the second access network device.

[0398] The first indication information of the second access network device is specifically used to indicate whether one or more cells managed by the second access network device support providing computing services.

[0399] The computing resource information of the second access network device is specifically used to instruct one or more cells managed by the second access network device to provide the relevant computing resources for the computing service.

[0400] And / or, the computing load information of the second access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the second access network device.

[0401] In one possible implementation, the computing resource information includes any one or more of the following:

[0402] Hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information.

[0403] In one possible implementation, the computational load information includes any one or more of the following:

[0404] It can process resource load information, store resource load information, or transmit resource load information.

[0405] In one possible implementation,

[0406] The transceiver module 1101 is also configured to send a second request to the target access network device, the second request instructing the terminal device to request a switch to the target access network device, the target access network device belonging to the one or more second access network devices;

[0407] The second request also includes: context information of the computing task that the terminal device requests to execute;

[0408] The context information of the computation task includes any one or more of the following:

[0409] The identification information of the computing task,

[0410] The application's identification information, wherein the application is related to the computing task.

[0411] The bearer information for the computing task, indicating the transmission path of the data carrying the computing task, includes: a Data Radio Bearer (DRB), and / or a Quality of Service (QoS) flow.

[0412] The identification information of the computing nodes that support the execution of the aforementioned computing tasks.

[0413] Alternatively, a second indication message may be provided, indicating that the computing task needs to be switched to the target access network device for continued execution.

[0414] In one possible implementation, the context information of the computation task further includes any one or more of the following:

[0415] The computational state information of the neural network model related to the computational task.

[0416] The type information of the neural network model,

[0417] The parameter information of the neural network model,

[0418] The neural network model uses key-value storage (KV) cache information.

[0419] The neural network model includes information from one or more intermediate layers.

[0420] The initial input feature information of the neural network model,

[0421] Alternatively, the output feature information of one or more intermediate layers of the neural network model.

[0422] In one possible implementation,

[0423] The transceiver module 1101 is further configured to receive a second response from the target access network device, the second response being a response to the second request, and the second response indicating the reason why the terminal device failed to switch to the target access network device.

[0424] In one possible implementation, the second response includes any one or more of the following information:

[0425] The target access network device does not support providing computing services.

[0426] The target access network device lacks sufficient computing resources.

[0427] The target access network device does not support the computing task requested by the terminal device.

[0428] Alternatively, the target access network device may not be connected to the computing node that supports the execution of the computing task.

[0429] In one possible implementation,

[0430] The transceiver module 1101 is also configured to receive measurement results from the terminal device, the measurement results indicating the measurement results of the terminal device for one or more neighboring cells;

[0431] The processing module 1102 is used to determine the target access network device from the one or more second access network devices based on the measurement results and the calculation information of the one or more second access network devices.

[0432] In another example, the communication device 1100 is applied to a first access network device, the communication device 1100 comprising:

[0433] The transceiver module 1101 is used to send a second request to the target access network device. The second request instructs the terminal device to request a switch to the target access network device. The second request includes context information of the computing task requested by the terminal device.

[0434] The transceiver module 1101 is also configured to receive a second response from the target access network device, the second response being a response to the second request.

[0435] In one possible implementation, the context information of the computation task includes any one or more of the following:

[0436] The identification information of the computing task,

[0437] The application's identification information, wherein the application is related to the computing task.

[0438] The bearer information for the computing task, indicating the transmission path of the data carrying the computing task, includes: a Data Radio Bearer (DRB), and / or a Quality of Service (QoS) flow.

[0439] The identification information of the computing nodes that support the execution of the aforementioned computing tasks.

[0440] Alternatively, a second indication message may be provided, indicating that the computing task needs to be switched to the target access network device for continued execution.

[0441] In one possible implementation, the second response indicates the reason why the terminal device failed to switch to the target access network device.

[0442] In one possible implementation, the second response includes any one or more of the following information:

[0443] The target access network device does not support providing computing services.

[0444] The target access network device lacks sufficient computing resources.

[0445] The target access network device does not support the computing task requested by the terminal device.

[0446] Alternatively, the target access network device may not be connected to the computing node that supports the execution of the computing task.

[0447] In another example, the communication device 1100 is applied to a target access network device, the communication device 1100 comprising:

[0448] The transceiver module 1101 is configured to receive a second request from a first access network device. The second request instructs a terminal device to request a switch to the target access network device and requests the target access network device to provide computing and communication services to the terminal device. The second request includes context information of the computing task that the terminal device requests to execute.

[0449] The transceiver module 1101 is further configured to send a second response to the first access network device based on the second request and the computing information of the target access network device, wherein the computing information of the target access network device indicates the computing capabilities supported by the target access network device.

[0450] In one possible implementation, the context information of the computation task includes any one or more of the following:

[0451] The identification information of the computing task,

[0452] The application's identification information, wherein the application is related to the computing task.

[0453] The bearer information for the computing task, indicating the transmission path of the data carrying the computing task, includes: a Data Radio Bearer (DRB), and / or a Quality of Service (QoS) flow.

[0454] The identification information of the computing nodes that support the execution of the aforementioned computing tasks.

[0455] Alternatively, a second indication message may be provided, indicating that the computing task needs to be switched to the target access network device for continued execution.

[0456] In one possible implementation, the context information of the computation task further includes any one or more of the following:

[0457] The computational state information of the neural network model related to the computational task.

[0458] The type information of the neural network model,

[0459] The parameter information of the neural network model,

[0460] The neural network model uses key-value storage (KV) cache information.

[0461] The neural network model includes information from one or more intermediate layers.

[0462] The initial input feature information of the neural network model,

[0463] Alternatively, the output feature information of one or more intermediate layers of the neural network model.

[0464] In one possible implementation, the second response indicates the reason why the terminal device failed to switch to the target access network device.

[0465] In one possible implementation, the second response includes any one or more of the following information:

[0466] The target access network device does not support providing computing services.

[0467] The target access network device lacks sufficient computing resources.

[0468] The target access network device does not support the computing task requested by the terminal device.

[0469] Alternatively, the target access network device may not be connected to the computing node that supports the execution of the computing task.

[0470] In one possible implementation, the computational information of the target access network device includes any one or more of the following:

[0471] The target access network device is associated with the identification information of the computing node, which is used to provide computing services.

[0472] The first indication information of the target access network device indicates whether the target access network device supports providing computing services.

[0473] The computing resource information of the target access network device indicates the computing resources related to the computing service.

[0474] Alternatively, the computing load information of the target access network device indicates the load status of the computing resources provided by the target access network device.

[0475] In one possible implementation, the computational information of the target access network device further includes:

[0476] The identification information of one or more cells managed by the target access network device;

[0477] Specifically, the first indication information of the target access network device is used to indicate whether one or more cells managed by the target access network device support providing computing services.

[0478] The computing resource information of the target access network device is specifically used to instruct one or more cells managed by the target access network device to provide the relevant computing resources for the computing service.

[0479] And / or, the computing load information of the target access network device is specifically used to indicate the load status of the computing resources provided by one or more cells managed by the target access network device.

[0480] In one possible implementation, the computing resource information includes any one or more of the following:

[0481] Hardware resource information, processing capacity information, storage capacity information, transmission resource information, or software resource information.

[0482] In one possible implementation, the computational load information includes any one or more of the following:

[0483] It can process resource load information, store resource load information, or transmit resource load information.

[0484] It should be understood that the specific procedures for each module to perform the above-mentioned corresponding processes have been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0485] The processing module 1102 in the above embodiments can be implemented by at least one processor or processor-related circuitry. The transceiver module 1101 can be implemented by a transceiver or transceiver-related circuitry. The transceiver module 1101 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0486] This application also provides another communication device, and FIG12 is another structural schematic diagram of the communication device according to an embodiment of this application. Referring to FIG12, the communication device 1200 includes a processor 1201.

[0487] Optionally, the communication device 1200 may also include a memory 1202.

[0488] Optionally, the communication device 1200 may also include a transceiver 1203.

[0489] In one possible implementation, the processor 1201, memory 1202, and transceiver 1203 are connected via a bus, and the memory 1202 stores computer instructions.

[0490] In one possible implementation, when the communication device 1200 includes an access network device, or the access network device includes a CU or DU, or a component (e.g., a chip), module, or unit within the access network device, the communication device 1200 can be used to perform the steps performed by the first access network device, the second access network device, and / or the target access network device in the above method embodiments, as described in the relevant descriptions in the above method embodiments.

[0491] Optionally, the processing module 1102 in the embodiment shown in FIG11 may be the processor 1201, and the transceiver module 1101 in the embodiment shown in FIG11 may be the transceiver 1203. Alternatively, the processing module 1102 in the embodiment shown in FIG11 may be the processor 1201, and the transceiver module 1101 in the embodiment shown in FIG11 may be the transceiver 1203.

[0492] This application also provides a communication device. Figure 13 is another structural schematic diagram of the communication device according to an embodiment of this application. Referring to Figure 13, the communication device 1300 can be a terminal device in the above method embodiments, or it can be a component (e.g., a chip), module, or unit of the terminal device in the above method embodiments. The communication device 1300 can be used to perform the operations performed by the terminal device in the above method embodiments.

[0493] Processors are mainly used to process data or signals, control communication devices, execute corresponding software programs, and process data from software programs.

[0494] It should be noted that this processor has weak signal processing capabilities and is unable to perform complex signal processing algorithms.

[0495] The memory is mainly used to store software programs and data. The radio frequency (RF) circuit is mainly used for the conversion between baseband signals and RF signals, as well as the processing of RF signals.

[0496] Antennas are primarily used for transmitting and receiving radio frequency signals in the form of electromagnetic waves.

[0497] Optionally, the communication device 1300 may also include input / output devices, such as a touch screen, a display screen, a keyboard, etc., primarily used to receive user input data and output data to the user.

[0498] When data needs to be transmitted, the processor performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit then processes the baseband signal and transmits it outward as electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts it into a baseband signal, and outputs the baseband signal to the processor. The processor then converts the baseband signal back into data and processes it.

[0499] For ease of explanation, only one memory and processor are shown in Figure 13. In actual communication device products, there may be one or more processors and one or more memories. Memory may also be called storage medium or storage device, etc. Memory may be set up independently of the processor or integrated with the processor; this application embodiment does not limit this.

[0500] In this embodiment, the antenna and radio frequency circuit with transceiver functions can be regarded as the transceiver unit of the communication device, and the processor with processing functions can be regarded as the processing unit of the communication device. As shown in FIG13, the communication device 1300 includes a transceiver unit 1310 and a processing unit 1320. The transceiver unit can also be called a transceiver, transceiver machine, transceiver device, etc. The processing unit can also be called a processor, processing board, processing module, processing device, etc.

[0501] Optionally, the devices in transceiver unit 1310 used for receiving functions can be considered as receiving units, and the devices in transceiver unit 1310 used for transmitting functions can be considered as transmitting units. That is, transceiver unit 1310 includes both receiving and transmitting units. A transceiver unit can also be called a transceiver, transceiver circuit, etc. A receiving unit can also be called a receiver, receiver, or receiving circuit, etc. A transmitting unit can also be called a transmitter, transmitter, or transmitting circuit, etc.

[0502] It should be understood that the transceiver unit 1310 is used to perform the transmission and reception operations of the first access network device, the second access network device, and / or the target access network device in the above method embodiments, and the processing unit 1220 is used to perform other operations on the first access network device, the second access network device, and / or the target access network device in the above method embodiments besides the transmission and reception operations.

[0503] When the communication device is a chip, the chip includes a transceiver unit and a processing unit. The transceiver unit can be an input / output circuit or a communication interface; the processing unit is a processor, microprocessor, integrated circuit, or logic circuit integrated on the chip. In the above method embodiment, the sending operation corresponds to the output of the input / output circuit, and the receiving operation corresponds to the input of the input / output circuit.

[0504] This application also provides a communication system, which includes a first access network device and a second access network device. The first access network device is used to perform all or part of the steps performed by the first access network device in the embodiment shown in FIG9, and the second access network device is used to perform all or part of the steps performed by the second access network device in the embodiment shown in FIG9.

[0505] This application also provides another communication system, which includes a first access network device and a target access network device. The first access network device is used to perform all or part of the steps performed by the first access network device in the embodiment shown in FIG10b, and the target access network device is used to perform all or part of the steps performed by the target access network device in the embodiment shown in FIG10b.

[0506] This application also provides a computer program product including computer instructions, which, when run on a computer, causes the computer to perform the methods of the embodiments shown in Figures 9 and 10b above.

[0507] This application also provides a computer-readable storage medium including computer instructions that, when executed on a computer, cause the computer to perform the methods of the embodiments shown in Figures 9 and 10b above.

[0508] This application also provides a chip device, including a processor, for calling a computer program or computer instructions stored in a memory to cause the processor to execute the method of the embodiments shown in FIG9 and FIG10b.

[0509] Optionally, the processor is coupled to the memory via an interface.

[0510] Optionally, the chip device may also include a memory in which computer programs or computer instructions are stored.

[0511] The processor mentioned above can be a general-purpose central processing unit, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of a program for controlling the methods of the embodiments shown in Figures 9 and 10b. The memory mentioned above can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, such as random access memory (RAM).

[0512] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, 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 coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between apparatuses or units through some interfaces, and may be electrical, mechanical, or other forms.

[0513] 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.

[0514] Furthermore, 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. The integrated unit can be implemented in hardware or as a software functional unit.

[0515] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the part of the technical solution that makes an essential contribution, or all or part 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, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0516] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A communication method characterized by comprising: The method is applied to a first access network device, and the method comprises: sending a first request, the first request comprising computing information of the first access network device, the computing information of the first access network device indicating computing capability supported by the first access network device; receiving a first response, the first response being a response to the first request, the first response comprising computing information of a second access network device, the computing information of the second access network device indicating computing capability supported by the second access network device.

2. The method of claim 1, wherein, The first request is used to request exchange of configuration data between the first access network device and the second access network device, the configuration data comprising: the computing information of the first access network device and / or the computing information of the second access network device.

3. The method of claim 2, wherein, The first request is specifically used to request exchange of application-level configuration data required for correct interoperation between the first access network device and the second access network device on an Xn-C interface, the application-level configuration data comprising: the computing information of the first access network device and / or the computing information of the second access network device.

4. The method according to any one of claims 1 to 3, characterized in that, The computing information of the first access network device comprises: identification information of a computing node associated with the first access network device, the computing node being used to provide a computing service, first indication information of the first access network device, the first indication information of the first access network device indicating whether the first access network device supports providing the computing service, computing resource information of the first access network device, the computing resource information of the first access network device indicating relevant computing resources of the computing service, or computing load information of the first access network device, the computing load information of the first access network device indicating a load condition of the computing resources provided by the first access network device; The computing information of the second access network device comprises: identification information of a computing node associated with the second access network device, the computing node being used to provide a computing service, first indication information of the second access network device, the first indication information of the second access network device indicating whether the second access network device supports providing the computing service, computing resource information of the second access network device, the computing resource information of the second access network device indicating relevant computing resources of the computing service, or computing load information of the second access network device, the computing load information of the second access network device indicating a load condition of the computing resources provided by the second access network device.

5. The method of claim 4, wherein, The computing information of the first access network device further comprises: identification information of one or more cells managed by the first access network device; The identification information of the computing node associated with the first access network device is specifically used to indicate a computing node associated with one or more cells managed by the first access network device, the first indication information of the first access network device is specifically used to indicate whether one or more cells managed by the first access network device support providing the computing service, The computing resource information of the first access network device specifically indicates relevant computing resources of one or more cells managed by the first access network device for providing the computing service, And / or, the computing load information of the first access network device specifically indicates a load condition of the computing resources provided by one or more cells managed by the first access network device. The computing information of the second access network device further includes: Identity information of one or more cells managed by the second access network device; The identity information of the computing node associated with the second access network device specifically indicates a computing node associated with one or more cells managed by the second access network device, The first indication information of the second access network device specifically indicates whether one or more cells managed by the second access network device support providing the computing service, The computing resource information of the second access network device specifically indicates relevant computing resources of one or more cells managed by the second access network device for providing the computing service, And / or, the computing load information of the second access network device specifically indicates a load condition of the computing resources provided by one or more cells managed by the second access network device.

6. The method according to claim 4 or 5, characterized in that, The computing resource information includes any one or more of the following information: Hardware resource information, processing capability information, storage capability information, transmission resource information, or software resource information.

7. The method according to any one of claims 4-6, characterized in that, The computing load information includes any one or more of the following information: Processing resource load information, storage resource load information, or transmission resource load information.

8. The method of any one of claims 1-7, further comprising: sending a second request to a target access network device, the second request indicating that the terminal device requests to handover to the target access network device, the target access network device belonging to the one or more second access network devices; the second request further including context information of a computing task requested to be executed by the terminal device; The context information of the computing task includes any one or more of the following information: Identity information of the computing task, Identity information of an application related to the computing task, Bearing information of the computing task, the bearing information indicating a transmission path of data bearing the computing task, the transmission path including a data radio bearer (DRB) and / or a quality of service (QoS) flow, Identity information of a computing node supporting execution of the computing task, Or second indication information indicating that the computing task needs to be handed over to the target access network device for continuous execution.

9. The method of claim 8, wherein, The context information of the computing task further includes any one or more of the following information: Computing state information of a neural network model related to the computing task, Type information of the neural network model, Parameter information of the neural network model, Key-value storage (KV Cache) information of the neural network model, Information of one or more intermediate layers included in the neural network model, Initial input feature information of the neural network model, Or, the output feature information of the one or more intermediate layers of the neural network model.

10. The method according to any one of claims 8-9, characterized in that, The method further includes: receiving a second response from the target access network device, the second response being a response to the second request, the second response indicating a reason for a failure of the terminal device to switch to the target access network device.

11. The method of claim 10, wherein, The second response includes any one or more of the following information: The target access network device does not support providing computing services, The target access network device lacks computing resources, The target access network device does not support the computing task requested by the terminal device, Or, the target access network device has no connection with a computing node that supports executing the computing task.

12. The method according to any one of claims 8-11, characterized in that, The method further includes: receiving a measurement result from the terminal device, the measurement result indicating a measurement result of the terminal device on one or more neighbor cells; determining the target access network device from the one or more second access network devices according to the measurement result and computing information of the one or more second access network devices.

13. A method of communication, comprising: The method is applied to a first access network device, and the method includes: sending a second request to a target access network device, the second request indicating that a terminal device requests to switch to the target access network device, the second request including context information of a computing task requested by the terminal device to execute; receiving a second response from the target access network device, the second response being a response to the second request.

14. The method of claim 13, wherein, The context information of the computing task includes any one or more of the following information: identification information of the computing task, identification information of an application, the application being related to the computing task, bearer information of the computing task, the bearer information indicating a transmission path of data carrying the computing task, the transmission path including a data radio bearer (DRB) and / or a quality of service (QoS) flow, identification information of a computing node that supports executing the computing task, Or, second indication information, the second indication information indicating that the computing task needs to switch to the target access network device for continuous execution.

15. The method according to claim 13 or 14, characterized in that, The second response indicates a reason for a failure of the terminal device to switch to the target access network device.

16. The method of claim 15, wherein, The second response includes any one or more of the following information: The target access network device does not support providing computing services, The target access network device lacks computing resources, The target access network device does not support the computing task requested by the terminal device, Or, the target access network device has no connection with a computing node that supports executing the computing task.

17. A method of communication, comprising: The method is applied to a target access network device, and the method includes: receiving a second request from a first access network device, the second request indicating that a terminal device requests to switch to the target access network device and requests the target access network device to provide computing services and communication services for the terminal device, the second request including context information of a computing task requested by the terminal device to execute; According to the second request and computing information of the target access network device, a second response is sent to the first access network device, and the computing information of the target access network device indicates computing capability supported by the target access network device.

18. The method of claim 17, wherein, The context information of the computing task includes any one or more of the following information: The identification information of the computing task, The identification information of an application related to the computing task, The bearer information of the computing task, the bearer information indicating a transmission path of data carrying the computing task, and the transmission path including a data radio bearer (DRB) and / or a quality of service (QoS) flow, The identification information of a computing node supporting execution of the computing task, Or second indication information indicating that the computing task needs to be switched to the target access network device for continuous execution.

19. The method of claim 17 or 18, wherein, The context information of the computing task further includes any one or more of the following information: The computing state information of a neural network model related to the computing task, The type information of the neural network model, The parameter information of the neural network model, The key-value cache (KV Cache) information of the neural network model, Information of one or more intermediate layers included in the neural network model, The initial input feature information of the neural network model, Or output feature information of the one or more intermediate layers of the neural network model.

20. The method of any one of claims 17-19, wherein, The second response indicates a reason for switching failure of the terminal device to the target access network device.

21. The method of claim 20, wherein, The second response includes any one or more of the following information: The target access network device does not support providing a computing service, The target access network device is insufficient in computing resources, The target access network device does not support the computing task requested by the terminal device, Or the target access network device has no connection with a computing node supporting execution of the computing task.

22. The method of any one of claims 17-21, wherein, The computing information of the target access network device includes any one or more of the following information: The identification information of a computing node associated with the target access network device, the computing node being configured to provide a computing service, First indication information of the target access network device, the first indication information of the target access network device indicating whether the target access network device supports providing a computing service, Computing resource information of the target access network device, the computing resource information of the target access network device indicating relevant computing resources of the computing service, Or computing load information of the target access network device, the computing load information of the target access network device indicating a load condition of the computing resources provided by the target access network device.

23. The method of claim 20, wherein, The computing information of the target access network device further includes: The identification information of one or more cells managed by the target access network device, The first indication information of the target access network device is specifically used to indicate whether one or more cells managed by the target access network device support providing a computing service, The computing resource information of the target access network device is specifically used to indicate relevant computing resources of the computing service provided by one or more cells managed by the target access network device, And / or, the computing load information of the target access network device is specifically used for indicating a load condition of the computing resource provided by one or more cells managed by the target access network device.

24. The method of claim 22 or 23, wherein, The computing resource information includes any one or more of the following information: Hardware resource information, processing capability information, storage capability information, transmission resource information, or software resource information.

25. The method of any one of claims 22-24, wherein, The computing load information includes any one or more of the following information: Processing resource load information, storage resource load information, or transmission resource load information.

26. A communications device, characterized by The communication device includes a module for performing the method of any one of claims 1-12, or claims 13-16, or claims 17-25.

27. A communications device, characterized by The communication device includes a processor for executing a computer program or computer instructions in a memory to perform the method of any one of claims 1-12, or to perform the method of any one of claims 13-16, or to perform the method of any one of claims 17-25.

28. A computer program product, characterised in that, When the computer program product runs on a computer, it makes the computer perform the method of any one of claims 1-12, or claims 13-16, or claims 17-25.

29. A computer-readable storage medium, characterized in that, A computer program is stored thereon, which is executed by the device to make the device perform the method of any one of claims 1-25.

Images