Communication method and apparatus

Abstract

A communication method and apparatus. In the method, a first network element receives a service request of a terminal device, wherein the service request is used for requesting to execute a first task; on the basis of a model associated with the first task and model deployment information, load and task completion state of each second network element among a plurality of second network elements, the first network element determines a plurality of third network elements for executing the first task and an execution policy of the first task, wherein the plurality of third network elements are some or all of the plurality of second network elements; and the first network element sends task configuration information to each third network element among the plurality of third network elements, wherein the task configuration information sent to each third network element comprises model configuration information of the third network element and the execution policy of the first task. The method makes it convenient for the plurality of third network elements to jointly execute, on the basis of the task configuration information, the first task requested by the terminal device.

Description

Communication method and apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411359128.7, filed on September 26, 2024, and entitled "A communication method and apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a communication method and apparatus. BACKGROUND

[0003] With the development of artificial intelligence (AI) technology and machine learning (ML) algorithms, deep learning models represented by neural networks have been applied in many fields. For example, a base station in a wireless network can complete an AI task requested by a terminal through an AI node deployed by the base station.

[0004] However, in a multi-station deployment communication scenario, how to jointly provide AI services for terminals by multiple stations remains to be studied. SUMMARY

[0005] Embodiments of the present application provide a communication method and apparatus, which are beneficial to jointly providing AI services for terminals by multiple stations.

[0006] In a first aspect, embodiments of the present application provide a communication method, which can be executed by a first network element. The first network element can refer to the first network element itself, or a processor, module, chip, or chip system in the first network element that implements the method. In the method, the first network element receives a service request of a terminal device, the service request being used to request execution of a first task; the first network element determines a plurality of third network elements for executing the first task and an execution strategy of the first task based on a model associated with the first task and model deployment information, load, and a task completion state of each of a plurality of second network elements, the plurality of third network elements being part or all of the plurality of second network elements; and the first network element sends task configuration information to each of the plurality of third network elements, the task configuration information sent to each of the plurality of third network elements including model configuration information of the third network element and the execution strategy of the first task.

[0007] It can be seen that, in the embodiment of the application, after the first network element receives the service request for requesting to perform the first task from the terminal device, the first network element can arrange a plurality of third network elements in the plurality of second network elements to perform the first task based on the model associated with the first task and the model deployment information, load and task completion state of each second network element in the plurality of second network elements, and inform each third network element of the model configuration information of the third network element and the execution strategy of the first task through the task configuration information, which is beneficial to the plurality of third network elements to jointly provide AI services for the terminal device based on the task configuration information and complete the execution of the first task.

[0008] In an optional implementation, the execution strategy of the first task includes at least one of the following: an order in which the plurality of third network elements perform the first task, and a subtask performed by each third network element in the plurality of third network elements, the subtask being a part of the first task.

[0009] In an optional implementation, in the case of a centralized communication scenario, the plurality of second network elements include a second network element of a serving cell and a second network element of a neighboring cell.

[0010] In another optional implementation, in the case of a distributed communication scenario, the plurality of second network elements are second network elements of neighboring cells.

[0011] In an optional implementation, before the first network element determines the plurality of third network elements performing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion state of each second network element in the plurality of second network elements, the first network element further performs the following steps: sending task request information to each second network element, the task request information being used to request to perform the first task, and the task request information including at least one of the following: an identifier of the first task, a computing power requirement corresponding to the first task, or a first service quality requirement corresponding to the first task; and receiving task response information of the plurality of second network elements, the task response information being used to respond to whether to perform the first task. In this way, the first network element determines the plurality of third network elements performing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion state of each second network element in the plurality of second network elements, which includes: determining the plurality of third network elements performing the first task and the execution strategy of the first task based on the task response information of the plurality of second network elements, the model associated with the first task and the model deployment information, load and task completion state of each second network element.

[0012] It can be seen that, before the first network element arranges the execution of the first task, the first network element can send task request information for requesting to perform the first task to each second network element in the plurality of second network elements, so as to arrange the execution of the first task based on the task response information fed back by each second network element. This way is beneficial to improving the reliability of the arrangement of the first task.

[0013] In an optional implementation, the service request includes a first service quality requirement corresponding to the first task, and the execution strategy of the first task includes an order in which the plurality of third network elements execute the first task. In this case, the task configuration information sent by the first network element to the i-th third network element further includes a second service quality requirement between the i-th third network element and the (i+1)-th third network element, and the second service quality requirement is determined based on the first service quality requirement.

[0014] In the above formula, the i-th third network element is a third network element arranged in the i-th position in the order in which the plurality of third network elements execute the first task, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements. The first service quality requirement corresponding to the first task refers to a service quality requirement required to execute the first task. The second service quality requirement between the i-th third network element and the (i+1)-th third network element refers to a service quality requirement required when the i-th third network element and the (i+1)-th third network element transmit data corresponding to the first task.

[0015] It can be seen that, in the case where the service request sent by the terminal device to the first network element includes a first service quality requirement corresponding to the first task, and the execution strategy of the first task includes an order in which the plurality of third network elements execute the first task, the first network element can further determine a second service quality requirement between the i-th third network element and the (i+1)-th third network element based on the first service quality requirement, and inform the i-th third network element, which is beneficial to the i-th third network element transmitting data corresponding to the first task to the (i+1)-th third network element based on the second service quality requirement, and can guarantee end-to-end service quality.

[0016] In an optional implementation, the task configuration information sent by the first network element to the i-th third network element further includes at least one of the following: an identifier of the (i+1)-th third network element, a data type transmitted between the i-th third network element and the (i+1)-th third network element, and a transmission mode between the i-th third network element and the (i+1)-th third network element. This mode is beneficial to the i-th third network element transmitting data corresponding to the first task to the (i+1)-th third network element based on at least one of the following: the identifier of the (i+1)-th third network element, the data type transmitted between the i-th third network element and the (i+1)-th third network element, and the transmission mode between the i-th third network element and the (i+1)-th third network element.

[0017] In an optional implementation, the first network element can receive first information of each second network element, and the first information of each second network element includes model deployment information, load, and task completion status of the second network element. This mode can enable the first network element to arrange execution of the first task based on the first information from the plurality of second network elements.

[0018] In an optional implementation, the first network element can further send first indication information to the i th third network element, and the first indication information sent to the i th third network element is used to instruct the i th third network element to establish a data channel with the (i+1) th third network element. This manner is beneficial for the i th third network element to establish a data channel with the (i+1) th third network element based on the first indication information, so as to transmit data corresponding to the first task through the data channel to the (i+1) th third network element.

[0019] In an optional implementation, the first indication information sent by the first network element to the i th third network element includes an identifier of the i th third network element and an identifier of the (i+1) th third network element.

[0020] In an optional implementation, the first indication information sent by the first network element to the i th third network element further includes at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of a first model used to execute the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the i th third network element and the (i+1) th third network element.

[0021] In an optional implementation, the first network element can further send second indication information to a fourth network element, and the second indication information includes core network information associated with the terminal device, and the fourth network element is a third network element in the plurality of third network elements that interacts with the server to transmit data corresponding to the first task. This manner is beneficial for the fourth network element to establish a data channel with the server in combination with the core network information associated with the terminal device, and further beneficial for the fourth network element to transmit data corresponding to the first task to the server based on the data channel.

[0022] In a second aspect, an embodiment of the present application further provides a communication method, which can be executed by a fifth network element. The fifth network element can refer to the fifth network element itself, or a processor, a module, a chip, or a chip system in the fifth network element that implements the method. In the method, the fifth network element receives task configuration information from a first network element, the task configuration information includes model configuration information and an execution strategy of a first task, and the first task is a task requested by a terminal device; and the fifth network element executes the first task based on the task configuration information.

[0023] As can be seen, in the embodiment of the present application, the fifth network element can execute the first task requested by the terminal device based on the task configuration information from the first network element, thereby realizing one link of jointly providing an AI service for the terminal device.

[0024] In an optional implementation, the fifth network element executes the first task based on the task configuration information, including: configuring a first model based on the model configuration information, the first model being a model used to execute the first task; and executing the first task based on the first model and the execution strategy of the first task.

[0025] In an optional implementation, the execution strategy of the first task includes at least one of the following: an order in which the plurality of third network elements execute the first task, and a subtask executed by each of the plurality of third network elements. The fifth network element is one of the plurality of third network elements, and the subtask is a part of the first task.

[0026] In an optional implementation, the fifth network element is an i-th network element in the order in which the plurality of third network elements execute the first task, and the task configuration information further includes a second quality of service requirement between the fifth network element and an (i+1)-th network element. The (i+1)-th network element is an (i+1)-th network element in the order in which the plurality of third network elements execute the first task, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements. In this way, the fifth network element can transmit data corresponding to the first task to the (i+1)-th network element based on the second quality of service.

[0027] In an optional implementation, the task configuration information further includes at least one of the following: an identifier of the (i+1)-th network element, a type of data transmitted between the fifth network element and the (i+1)-th network element, and a transmission mode between the fifth network element and the (i+1)-th network element. In this way, the fifth network element can transmit data corresponding to the first task to the (i+1)-th network element based on at least one of the following: the identifier of the (i+1)-th network element, the type of data transmitted between the fifth network element and the (i+1)-th network element, and the transmission mode between the fifth network element and the (i+1)-th network element.

[0028] In an optional implementation, the fifth network element can further send first information, and the first information includes model deployment information, a load, and a task completion state of the fifth network element. In this way, the first network element can schedule execution of the first task based on the first information of the fifth network element.

[0029] In an optional implementation, the fifth network element can further perform the following steps: receiving first indication information, the first indication information being used to indicate that the fifth network element establishes a data channel with the (i+1)-th network element; and based on the first indication information, establishing the data channel with the (i+1)-th network element. The fifth network element is an i-th network element in the order in which the plurality of third network elements execute the first task, and the (i+1)-th network element is an (i+1)-th network element in the order in which the plurality of third network elements execute the first task.

[0030] As can be seen, the fifth network element can establish a data channel with the (i+1)-th network element based on the received first indication information, so as to subsequently transmit data corresponding to the first task to the (i+1)-th network element.

[0031] In an optional implementation, the first indication information includes an identifier of the fifth network element and an identifier of the (i+1)-th network element.

[0032] In an optional implementation, the first indication information further includes at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of the first model used for executing the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the fifth network element and the i+1th third network element.

[0033] In an optional implementation, when the execution strategy of the first task includes a sequence in which the plurality of third network elements execute the first task, the fifth network element can further establish a data channel with the i+1th third network element according to the sequence in which the plurality of third network elements execute the first task.

[0034] In an optional implementation, when the data corresponding to the first task obtained by the fifth network element needs to flow to the server, the fifth network element further performs the following steps: receiving second indication information, the second indication information including core network information associated with the terminal device; and establishing a data channel with the server based on the core network information associated with the terminal device. It can be seen that when the data corresponding to the first task obtained by the fifth network element needs to flow to the server, the core network information associated with the terminal device can be used to establish a data channel with the server, so as to transmit the data corresponding to the first task to the server through the data channel.

[0035] In a third aspect, the embodiments of the present application further provide a communication apparatus. The communication apparatus has part or all functions of the first network element in the first aspect, or part or all functions of the fifth network element in the second aspect. For example, the communication apparatus can have the functions of part or all embodiments of the first network element in the first aspect, or have the functions of any one of the embodiments of the present application. The functions can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more units or modules corresponding to the functions.

[0036] In a possible design, the communication apparatus can include a processing unit and a communication unit. The processing unit is configured to support the communication apparatus to perform the corresponding functions in the above methods. The communication unit is configured to support the communication between the communication apparatus and other communication apparatuses. The communication apparatus can further include a storage unit configured to be coupled to the processing unit and the communication unit, and store the necessary program instructions and data of the communication apparatus.

[0037] In an embodiment, the communication apparatus includes a processing unit and a communication unit, and the apparatus is applied to a first network element.

[0038] The communication unit is configured to receive a service request of a terminal device, the service request being used to request to execute a first task.

[0039] The processing unit is configured to determine a plurality of third network elements for executing the first task and an execution strategy of the first task based on a model associated with the first task and model deployment information, load and task completion status of each of a plurality of second network elements, the plurality of third network elements being part or all of the plurality of second network elements.

[0040] The communication unit is further configured to send task configuration information to each of the plurality of third network elements, the task configuration information sent to each of the plurality of third network elements including model configuration information of the third network element and the execution strategy of the first task.

[0041] In addition, in this aspect, other optional implementations of the communication device can refer to the related content of the first aspect described above, which will not be described in detail here.

[0042] In another implementation, the communication device includes a processing unit and a communication unit, and the device is applied to a fifth network element.

[0043] The communication unit is configured to receive task configuration information from a first network element, the task configuration information including model configuration information and an execution strategy of a first task, the first task being a task requested to be executed by a terminal device.

[0044] The processing unit is configured to execute the first task based on the task configuration information.

[0045] In addition, in this aspect, other optional implementations of the communication device can refer to the related content of the second aspect described above, which will not be described in detail here.

[0046] For example, the communication unit can be a transceiver or a communication interface, the storage unit can be a memory, and the processing unit can be a processor.

[0047] In one implementation, the communication device includes a processor and a transceiver, and the device is applied to a first network element.

[0048] The transceiver is configured to receive a service request of a terminal device, the service request being used to request to execute a first task.

[0049] The processing unit is configured to determine a plurality of third network elements for executing the first task and an execution strategy of the first task based on a model associated with the first task and model deployment information, load and task completion status of each of a plurality of second network elements, the plurality of third network elements being part or all of the plurality of second network elements.

[0050] The transceiver is further configured to send task configuration information to each of the plurality of third network elements, wherein the task configuration information sent to each of the third network elements comprises model configuration information of the third network element and the execution strategy of the first task.

[0051] In addition, in this aspect, other optional implementation of the communication device can refer to the related content of the first aspect described above, which will not be described in detail here.

[0052] In another implementation, the communication device comprises a processor and a transceiver, and the device is applied to a fifth network element.

[0053] The transceiver is configured to receive task configuration information from a first network element, wherein the task configuration information comprises model configuration information and an execution strategy of a first task, and the first task is a task requested to be executed by a terminal device.

[0054] The processor is configured to execute the first task based on the task configuration information.

[0055] In addition, in this aspect, other optional implementation of the communication device can refer to the related content of the second aspect described above, which will not be described in detail here.

[0056] In another implementation, the communication device is a chip or a chip system. The processing unit can also be implemented as a processing circuit or a logic circuit; and the communication unit can be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin or related circuit on the chip or chip system.

[0057] In the implementation process, the processor can be configured to perform, for example but not limited to, baseband related processing, and the transceiver can be configured to perform, for example but not limited to, radio frequency transmission and reception. The above-mentioned devices can be respectively arranged on independent chips, or at least part or all of them can be arranged on the same chip. For example, the processor can be further divided into an analog baseband processor and a digital baseband processor. Among them, the analog baseband processor can be integrated on the same chip as the transceiver, and the digital baseband processor can be arranged on an independent chip. With the continuous development of integrated circuit technology, more and more devices can be integrated on the same chip. For example, the digital baseband processor can be integrated on the same chip as various application processors (such as but not limited to, graphic processors, multimedia processors, etc.). Such a chip can be called a system on a chip (SoC). Whether to arrange each device independently on different chips or to integrate them on one or more chips often depends on the needs of product design. The implementation form of the above-mentioned devices is not limited in the embodiments of the present application.

[0058] In a fourth aspect, the embodiments of the present application further provide a processor for executing the methods described above. In the process of executing the methods, the processes of sending and receiving the information described above in the methods can be understood as the processes of outputting the information described above by the processor and the processes of receiving the input information described above by the processor. When the information described above is outputted, the processor outputs the information described above to the transceiver so as to be transmitted by the transceiver. After the information described above is outputted by the processor, it can also need to be processed further before reaching the transceiver. Similarly, when the processor receives the input information described above, the transceiver receives the information described above and inputs it to the processor. Furthermore, after the transceiver receives the information described above, the information described above can need to be processed further before being inputted to the processor.

[0059] For the sending and receiving operations and the like involved in the processor, if no special description is given, or if it does not contradict the actual role or inherent logic in the related description, it can be more generally understood as the outputting and receiving, inputting operations of the processor, rather than the sending and receiving operations directly performed by the radio frequency circuit and the antenna.

[0060] In the implementation process, the processor can be a processor specially used for executing the methods, or a processor executing computer instructions in a memory to execute the methods, such as a general processor. The memory can be a non-transitory memory, such as a read only memory (ROM), which can be integrated on the same chip with the processor, or can be arranged on different chips respectively, and the type of the memory and the arrangement mode of the memory and the processor are not limited in the embodiments of the present application.

[0061] In a fifth aspect, the embodiments of the present application further provide a communication system, which includes a first network element and a plurality of second network elements. In another possible design, the system can further include other devices / function network elements interacting with the first network element and the plurality of second network elements.

[0062] In a sixth aspect, the embodiments of the present application provide a computer readable storage medium for storing instructions, when the instructions are run on a computer, the method in the first aspect or the second aspect is implemented.

[0063] In a seventh aspect, the embodiments of the present application further provide a computer program product including instructions, when the instructions are run on a computer, the method in the first aspect or the second aspect is implemented.

[0064] In an eighth aspect, an embodiment of the present application provides a chip system, which comprises a processor and an interface, the interface is configured to acquire a program or an instruction, and the processor is configured to invoke the program or the instruction to implement or support a first network element to implement the functions related to the first aspect, or to implement or support a fifth network element to implement the functions related to the second aspect. For example, at least one of the data and the information related to the above method is determined or processed. In a possible design, the chip system further comprises a memory, and the memory is configured to store necessary program instructions and data of the terminal. The chip system can be composed of a chip, or can comprise a chip and other discrete devices.

[0065] In a ninth aspect, an embodiment of the present application provides a communication apparatus, comprising a processor, configured to execute computer programs or executable instructions stored in a memory, when the computer programs or executable instructions are executed, the apparatus performs the method in each possible implementation of the first aspect or the second aspect.

[0066] In a possible implementation, the processor and the memory are integrated together.

[0067] In another possible implementation, the memory is located outside the communication apparatus.

[0068] The advantages of the third aspect to the ninth aspect can refer to the advantages of the first aspect or the second aspect, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0069] FIG. 1 is a schematic diagram of an application framework;

[0070] FIG. 2 is a schematic diagram of another application framework;

[0071] FIG. 3 is a schematic diagram of a system architecture;

[0072] FIG. 4 is a schematic diagram of another system architecture;

[0073] FIG. 5 is an interaction schematic diagram of a communication method provided by an embodiment of the present application;

[0074] FIG. 6 is an interaction schematic diagram of another communication method provided by an embodiment of the present application;

[0075] FIG. 7 is an interaction schematic diagram of yet another communication method provided by an embodiment of the present application;

[0076] FIG. 8 is a structural schematic diagram of a communication apparatus provided by an embodiment of the present application;

[0077] FIG. 9 is a structural schematic diagram of another communication apparatus provided by an embodiment of the present application. DETAILED DESCRIPTION

[0078] The technical solutions in the present application will be described below with reference to the drawings.

[0079] The technical solutions provided in the present application can be applied to various communication systems, for example: a 5th generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system such as a 6th generation (6G) mobile communication system, or a converged system of multiple systems, etc. The technical solutions provided in the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and an internet of things (IoT) communication system or other communication systems.

[0080] A network element in a communication system can send a signal to another network element or receive a signal from another network element. The signal can include information, signaling, or data, etc. The network element can also be replaced by an entity, a network entity, a device, a communication device, a communication module, a node, a communication node, etc. The present disclosure describes the network element as an example. For example, the communication system can include at least one terminal device and at least one network device. The network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the network device.

[0081] In the embodiments of the present application, the terminal device can also be referred to as a user equipment (UE), an access terminal, a user unit, a user station, a mobile station, a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent or a user apparatus. The terminal device can be a device providing voice / data, such as a handheld device with wireless connection function, a vehicle-mounted device, etc. At present, some examples of the terminal are: a mobile phone, a tablet computer, a notebook computer, a palm computer, a mobile internet device (MID), a wearable device, a virtual reality (VR) device, an augmented reality (AR) device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home, a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a handheld device with wireless communication function, a computing device or other processing device connected to a wireless modem, a wearable device, a terminal device in a 5G network or a terminal device in a future evolved public land mobile network (PLMN), etc., and the embodiments of the present application are not limited thereto.

[0082] By way of example and not limitation, in embodiments of the present application, the terminal device can also be a wearable device. The wearable device can also be referred to as a wearable smart device, which is a general term for devices that are designed and developed by applying wearable technology to daily wear, such as glasses, gloves, watches, clothing, and shoes. The wearable device is a portable device that is directly worn on the body or integrated into the clothes or accessories of the user. The wearable device is not only a hardware device, but also has strong functions through software support and data interaction and cloud interaction. The general wearable smart device includes a full function, a large size, and can realize complete or partial functions without relying on a smart phone, such as a smart watch or smart glasses, and focuses on a certain application function and needs to be used in cooperation with other devices, such as a smart phone, such as various smart wristbands and smart jewelry for monitoring vital signs.

[0083] In embodiments of the present application, the device for implementing the function of the terminal device can be a terminal device, or a device capable of supporting the terminal device to implement the function, such as a chip system, which can be installed in the terminal device or used in matching with the terminal device. In embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices. In embodiments of the present application, only the device for implementing the function of the terminal device is taken as an example for description, and the present application is not limited to the scheme.

[0084] The network device in the embodiments of the present application can be a device for communicating with a terminal device, and the network device can also be referred to as an access network device or a radio access network device, for example, the network device can be a base station. The network device in the embodiments of the present application can refer to a radio access network (RAN) node (or device) for accessing a terminal device to a wireless network. The base station can broadly cover various names in the following or be replaced by the following names, such as: Node B (NodeB), evolved Node B (eNB), next generation Node B (gNB), relay station, access point, transmitting and receiving point (TRP), transmitting point (TP), primary station, secondary station, motor slide retainer (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DU), radio unit (RU), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a master node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip used in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device assuming a base station function in D2D, V2X, M2M communication, a network side device in 6G network, a device assuming a base station function in future communication system, etc. The base station can support networks of the same or different access technologies. Optionally, the RAN node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, etc. For example, the access network device in V2X technology can be a road side unit (RSU). The embodiments of the present application do not limit the specific technology and specific device form of the network device.

[0085] The base station can be fixed or mobile. For example, a helicopter or a drone can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station. In other examples, the helicopter or the drone can be configured to serve as a device communicating with another base station.

[0086] In some deployments, the network device mentioned by embodiments of the present application can be a device including a CU, or a DU, or a device including a CU and a DU, or a control plane CU node (central unit-control plane (CU-CP)) and a user plane CU node (central unit-user plane (CU-UP)) and a DU node. For example, the network device can include a gNB-CU-CP, a gNB-CU-UP and a gNB-DU.

[0087] In some deployments, wireless access by a terminal is assisted by cooperation of multiple RAN nodes, and different RAN nodes respectively implement part of the functions of a base station. For example, the RAN node can be a CU, a DU, a CU-CP, a CU-UP, or an RU, etc. The CU and the DU can be separately arranged, or can also be included in the same network element, for example, in a BBU. The RU can be included in a radio frequency device or a radio frequency unit, for example, included in an RRU, an AAU or an RRH.

[0088] The RAN node can support one or more types of front interfaces, and different front interfaces respectively correspond to DUs and RUs with different functions. If the front interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more of the baseband functions, and the RU is configured to implement one or more of the radio frequency functions. If the front interface between the DU and the RU is another interface, compared with the CPRI, part of the baseband functions of the downlink and / or uplink, such as one or more of precoding, digital beamforming (BF), or fast inverse fast Fourier transform (IFFT) / adding a cyclic prefix (CP) for the downlink, or one or more of digital beamforming (BF), or fast Fourier transform (FFT) / removing a cyclic prefix (CP) for the uplink, are moved from the DU to the RU for implementation. In a possible implementation, the interface can be an enhanced common public radio interface (eCPRI). Under the eCPRI architecture, the splitting manner between the DU and the RU is different, corresponding to different categories (Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, F.

[0089] Taking eCPRI Cat A as an example, for downlink transmission, with layer mapping as the cut, the DU is configured to implement one or more functions (i.e., one or more of encoding, rate matching, scrambling, modulation, layer mapping) before layer mapping, and other functions (e.g., one or more of resource element (RE) mapping, digital beamforming (BF), or inverse fast Fourier transform (IFFT) / adding cyclic prefix (CP)) after layer mapping are implemented in the RU. For uplink transmission, with RE demapping as the cut, the DU is configured to implement one or more functions (i.e., one or more of decoding, de-rate matching, de-scrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, RE demapping) before demapping, and other functions (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) after demapping are implemented in the RU. It can be understood that the function description of the DU and the RU corresponding to various types of eCPRI can refer to the eCPRI protocol, which is not described here.

[0090] In a possible design, the processing unit in the BBU for implementing baseband functions is referred to as a base band high (BBH) unit, and the processing unit in the RRU / AAU / RRH for implementing baseband functions is referred to as a base band low (BBL) unit.

[0091] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0092] In the embodiments of the present application, the apparatus for implementing the function of the network device can be a network device, or an apparatus capable of supporting the network device to implement the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module. The apparatus can be installed in the network device or used in combination with the network device. In the embodiments of the present application, only the apparatus for implementing the function of the network device is taken as an example for illustration, and the present application is not limited in this regard.

[0093] The network device and / or the terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can also be deployed on water surface; and can also be deployed on aircraft, balloons and satellites in the air. The present application does not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or software functions running on special hardware, software functions running on general hardware, such as virtualized functions instantiated on a platform (for example, a cloud platform), or entities including special or general hardware devices and software functions. The present application does not limit the specific forms of the terminal device and the network device.

[0094] In order to support AI technology in a wireless network, AI nodes can also be introduced into the network.

[0095] Optionally, the AI node can be deployed in one or more of the following positions in the communication system: an access network device, a terminal device, or a core network device, etc., or the AI node can also be deployed separately, for example, in a host or a cloud server of an over the top (OTT) system. The AI node can communicate with other devices in the communication system, which can be one or more of the following: a network device, a terminal device, or a network element of a core network, etc.

[0096] It can be understood that the present application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on functions, such as different AI nodes responsible for different functions.

[0097] It can also be understood that the AI node can be a separate device, or can be integrated into the same device to implement different functions, or can be a network element in a hardware device, or can be a software function running on special hardware, or a virtualized function instantiated on a platform (for example, a cloud platform). The present application does not limit the specific forms of the AI node. The AI node can be an AI network element or an AI module.

[0098] Figure 1 is a schematic diagram of an application framework. As shown in Figure 1, network elements in a communication system are connected through interfaces (e.g., NG, Xn), or air interfaces. One or more AI modules (only one is shown in Figure 1 for clarity) are deployed in one or more of the network element nodes, such as a core network device, an access network node or device (RAN node or device), a terminal, or one or more devices in operations, administration and maintenance (OAM). The access network node can be a standalone RAN node, or can include multiple RAN nodes, e.g., including a CU and a DU. The CU and / or the DU can also be provided with one or more AI modules. Optionally, the CU can be further split into a CU-CP and a CU-UP. The CU-CP and / or the CU-UP can be provided with one or more AI modules.

[0099] The AI modules are configured to implement corresponding AI functions. The AI modules deployed in different network elements can be the same or different. The AI modules can implement different functions according to different parameter configurations of the models of the AI modules. The models of the AI modules can be configured based on one or more of the following parameters: a structural parameter (e.g., at least one of a number of layers of a neural network, a width of a neural network, a connection relationship between layers, a weight of a neuron, an activation function of a neuron, or a bias in the activation function), an input parameter (e.g., a type of the input parameter and / or a dimension of the input parameter), or an output parameter (e.g., a type of the output parameter and / or a dimension of the output parameter). The bias in the activation function can also be referred to as a bias of the neural network.

[0100] One AI module can have one or more models. One model can infer an output including one parameter or multiple parameters. The learning process, the training process, or the inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0101] Figure 2 is another schematic diagram of an application framework. As shown in Figure 2, a RAN intelligent controller (RIC) is included in a communication system. The RIC can be an AI module shown in Figure 1, and is configured to implement AI-related functions. The RIC includes a near-real time RIC (near-RT RIC), and a non-real time RIC (Non-RT RIC). The Non-RT RIC is mainly configured to process non-real time information, such as data that is not sensitive to latency, and the latency of the data can be in seconds. The near-RT RIC is mainly configured to process near-real time information, such as data that is relatively sensitive to latency, and the latency of the data is in tens of milliseconds.

[0102] The near-real-time RIC is used for model training and inference. For example, it is used for training an AI model, and inference is performed using the AI model. The near-real-time RIC can obtain network-side and / or terminal-side information from a RAN node (for example, a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data. Optionally, the near-real-time RIC can deliver inference results to the RAN node and / or the terminal. Optionally, the inference results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near-real-time RIC delivers the inference results to the DU, which then delivers them to the RU.

[0103] The non-real-time RIC is also used for model training and inference. For example, it is used for training an AI model, and inference is performed using the model. The non-real-time RIC can obtain network-side and / or terminal-side information from a RAN node (for example, a CU, a CU-CP, a CU-UP, a DU, and / or a RU) and / or a terminal. The information can be used as training data or inference data, and the inference results can be delivered to the RAN node and / or the terminal. Optionally, the inference results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC delivers the inference results to the DU, which then delivers them to the RU.

[0104] The near-real-time RIC and the non-real-time RIC can also be separately set up as a network element. Alternatively, the near-real-time RIC and the non-real-time RIC can also be part of other devices. For example, the near-real-time RIC is set up in a RAN node (for example, a CU, a DU), and the non-real-time RIC is set up in an OAM, a cloud server, a core network device, or another network device.

[0105] Embodiments of the present application can be applied to application scenarios of providing distributed AI services in a wireless network. For example, FIG. 3 and FIG. 4 are schematic diagrams of a system architecture to which embodiments of the present application are applicable. Specifically, FIG. 3 is a schematic diagram of a system architecture for a centralized communication scenario, and FIG. 4 is a schematic diagram of a system architecture for a distributed communication scenario. The system architecture shown in FIG. 3 and FIG. 4 includes an application server (APP server), a core network (CN), a RAN, and a terminal device.

[0106] As shown in FIG. 3 and FIG. 4, an AI node (such as a service unit (SU)) is introduced on the RAN side. The SU is a platform for deploying AI applications, models, and data, and can perform AI tasks by virtue of its added computing power. Optionally, the business logic can be designed to have computing power on the terminal, network, and cloud sides.

[0107] In the centralized architecture shown in FIG. 3, the upper-layer central node is responsible for the response, establishment and control of the AI function, such as a functional network element (new network element or functional extension of the original network element) on the core network side, an independent control node on the RAN side, an anchor RAN node, etc. The functional network element on the core network side can be, for example, an artificial intelligence management function (AIMF) network element deployed. In the distributed architecture shown in FIG. 4, the AI control network element is located in each AI node, which can be a SU function module or a dedicated control node in the base station, and the establishment of the task data channel is completed through the negotiation of the inter-station control module. The AI control network element can be, for example, an AIMF network element.

[0108] It can be seen that the functions of the original network elements in the communication system architecture remain unchanged, the newly added AI nodes / network elements are responsible for providing the execution of AI tasks, and the AI control function network element is responsible for the data channel establishment of the distributed AI tasks. The AI control function network element can be a newly added functional network element or a functional extension of the original network element.

[0109] Embodiments disclosed in the present application will present various aspects, embodiments or features of the present application around systems including a plurality of devices, components, modules, etc. It should be understood and appreciated that each system can include additional devices, components, modules, etc., and / or can not include all the devices, components, modules, etc. discussed in connection with the drawings. In addition, combinations of these solutions can also be used.

[0110] It should be understood that, in the present application, the indication includes direct indication (also known as explicit indication) and implicit indication. Among them, the direct indication of information A means including the information A; the implicit indication of information A means indicating the information A through the corresponding relationship between the information A and the information B and the direct indication of the information B. The corresponding relationship between the information A and the information B can be predefined, pre-stored, pre-burned or pre-configured.

[0111] In the embodiments of the present application, "network element A sends information A to network element B" can be understood as that the destination of the information A or the intermediate network element in the transmission path between the destination is network element B, which can include direct or indirect sending of information to network element B. "Network element B receives information A from network element A" can be understood as that the source of the information A or the intermediate network element in the transmission path between the source is network element A, which can include direct or indirect receiving of information from network element A. The information can be processed as necessary between the source and the destination of the information sending, such as format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be understood similarly, which will not be described here.

[0112] In a possible manner, for a centralized communication scenario, the first network element in the embodiment of the present application is a central node responsible for the response, establishment and control of the AI function, which can be deployed at the CN side or at the RAN side. For ease of description, the first network element is taken as an AI management function (AIMF) network element deployed at the CN side in the following description; the second network element in the embodiment of the present application is an AI node deployed at the RAN side. For ease of description, the second network element is taken as a SU deployed at the RAN side in the following description. In addition, the second network element includes an AI node of a serving cell and an AI node of a neighboring cell, such as the second network element including a SU of a serving cell and a SU of a neighboring cell. The SU of the serving cell refers to a SU deployed in a serving node, and the serving node is an RAN node currently providing network services for the terminal device. The SU of the serving cell can be represented by s-SU. The SU of the neighboring cell refers to a SU deployed in a neighboring node, and the neighboring node is an RAN node adjacent to the serving node of the terminal device. The SU of the neighboring cell can be represented by n-SU, and n-SU is one or more.

[0113] In another possible manner, for a distributed communication scenario, the first network element in the embodiment of the present application is an AI node in a serving cell. For ease of description, the first network element is taken as an s-SU in the following description; the second network element in the embodiment of the present application is an AI node of a neighboring cell. For ease of description, the second network element is taken as an n-SU in the following description.

[0114] The embodiments of the present application are described in detail below with reference to the accompanying drawings. The embodiments of the present application take a terminal device, a first network element and a fifth network element as an execution subject to illustrate a corresponding method, and the fifth network element is one of a plurality of third network elements, and the plurality of third network elements are part or all of a plurality of second network elements. However, the present application does not limit the execution subject of the method. For example, the terminal device in the method can also be a processor, a module, a chip, or a chip system or a software module supporting the implementation of the corresponding method.

[0115] The embodiment of the present application proposes a communication method, and FIG. 5 is an interaction diagram of the communication method. The communication method includes but is not limited to the following steps:

[0116] S501. The terminal device sends a service request, and the service request is used to request to perform a first task. Correspondingly, the first network element receives the service request of the terminal device.

[0117] Understandably, the terminal device sends a service request for requesting to perform the first task to the first network element in the case of needing to request the network to perform the first task, so that the first network element orchestrates the performance of the first task. Wherein, the first task can be a task associated with an application, or in other words, the first task is a task belonging to an application. For example, the first task is to identify picture #1 output by application #1, and the first task is a task associated with application #1. For another example, the first task is to process video #1 output by application #2, and the first task is a task belonging to application #2.

[0118] In a possible manner, the service request includes an identification of the first task, which can be configured by the terminal device in advance for the first task.

[0119] In a possible manner, the service request can also be referred to as an AI service request, and the AI service request is specifically used to request to perform the first task through an AI model. This manner is beneficial for the network to perform the first task requested by the terminal device through the AI model, that is, beneficial for the network to provide AI services for the terminal device through the model.

[0120] In a possible manner, the service request further includes capability information of the terminal device, and the capability information of the terminal device includes at least one of the following: computing power of the terminal device, load of the terminal device, and remaining resources of the terminal device. This manner is beneficial for the first network element to determine whether to orchestrate the terminal device to perform the first task based on the capability information of the terminal device when orchestrating the performance of the first task.

[0121] In a possible manner, the service request further includes a first quality of service requirement corresponding to the first task, and the first quality of service requirement corresponding to the first task refers to a quality of service (QoS) requirement required to perform the first task. The QoS requirement includes at least one of the following: transmission delay, execution delay, energy consumption, and service accuracy. This manner is beneficial for the first network element to orchestrate the performance of the first task based on the quality of service requirement corresponding to the first task, so that the first task can be performed under the condition of meeting the first quality of service requirement, and the end-to-end AI service quality can be guaranteed.

[0122] In an optional implementation, when the first network element is an AIMF network element, the terminal device can send the service request to the access network device through a radio resource control (RRC) message, and the access network device forwards the service request of the terminal device to the AIMF network element through a non-access layer (NAS) / new AI control protocol layer, such as the CU of the access network device forwarding the service request of the terminal device to the AIMF through the SU.

[0123] In another alternative implementation, when the first network element is an SU (s-SU) deployed in a service node, the terminal device can send a service request to the access network device through an RRC message, and the access network device forwards the service request of the terminal device to the s-SU through a new AI control protocol layer, for example, the CU of the access network device forwards the service request of the terminal device to the s-SU through the new AI control protocol layer.

[0124] S502. The first network element determines, based on the model associated with the first task and the model deployment information, load and task completion status of each of the plurality of second network elements, a plurality of third network elements for executing the first task and an execution strategy of the first task.

[0125] The plurality of third network elements are part or all of the plurality of second network elements.

[0126] In one possible manner, when the first network element is an AIMF, the plurality of second network elements include a second network element of a serving cell and a second network element of a neighboring cell, for example, the plurality of second network elements include an s-SU and an n-SU.

[0127] In another possible manner, when the first network element is a second network element of a serving cell, the plurality of second network elements are second network elements of neighboring cells. For example, when the first network element is an s-SU, the plurality of second network elements are a plurality of n-SUs.

[0128] The model associated with the first task can refer to a model of an application contract to which the first task belongs, and the model of the application contract includes one or more AI models. The one or more AI models of the application contract can be understood as the one or more AI models can be used to process the task corresponding to the application. For example, the first task is to perform image recognition on image 1 generated by application a, and the model associated with the first task is the AI model contracted by application a, for example, the contracted AI model is model 1 and model 2, and model 1 and model 2 can be used to process the task corresponding to application a, such as the first task.

[0129] The model deployment information of the second network element includes the identification of the AI model / AI application deployed by the second network element and the function of the deployed AI model / AI application. For example, the second network element is an s-SU, the models deployed by the s-SU locally include model 1 and model 2, model 1 is used for image recognition, and model 2 is used for question answering, and the model deployment information of the s-SU includes the identification of model 1 and the identification of model 2, and the application indicates that the function of model 1 is image recognition and the function of model 2 is question answering.

[0130] The load of the second network element refers to the proportion of the occupation of the computing resources of the second network element, or the memory / video memory occupation, such as the load of the second network element is 80%, which means that the remaining memory of the second network element is 80%. The load can also be replaced by "computing resource state".

[0131] The task completion state of the second network element refers to the completion degree / residual computing time of the second network element using a certain AI model / AI application to perform a certain task at the current time. For example, the second network element uses model 1 to process video 1 at the current time, and 30% of video 1 has been processed, then the task completion state of the second network element refers to the progress of using model 1 to process video 1 is 30%. The task completion state can also be replaced by "task execution state".

[0132] In an optional implementation, the execution strategy of the first task includes at least one of the following: an execution order of the plurality of third network elements to execute the first task, and a subtask executed by each of the plurality of third network elements. The execution order of the first task can also be referred to as a task execution logical relationship of the first task. In addition, the execution order of the first task by some of the plurality of third network elements can be the same or different. For example, the plurality of third network elements include third network element #1, third network element #2, and third network element #3, and the execution order of the first task by the third network element #1, the third network element #2, and the third network element #3 is: third network element #1→third network element #2→third network element #3, then the execution order of the first task by the third network element #1, the third network element #2, and the third network element #3 is different. For another example, the plurality of third network elements include third network element #1, third network element #2, and third network element #3, and the execution order of the first task by the third network element #1, the third network element #2, and the third network element #3 is: third network element #1, third network element #2→third network element #3, then the third network element #1 and the third network element #2 execute the first task at the same time, and the third network element #3 executes the first task again, that is, the execution order of the first task by the third network element #1 and the third network element #2 is the same.

[0133] In addition, the subtask is a part of the first task, such as the first task is composed of subtask 1, subtask 2, and subtask 3, or the first task can be split into subtask 1, subtask 2, and subtask 3. It should be noted that the execution of the first task in this paper can refer to the execution of the first task itself, or the execution of the subtask of the first task. For example, when the first network element does not split the first task into multiple subtasks, the plurality of third network elements execute the first task, which can be understood as: the plurality of third network elements all execute the first task itself. For another example, when the first network element splits the first task into multiple subtasks, the plurality of third network elements execute the first task, which can be understood as: each of the plurality of third network elements executes a subtask of the first task, and some of the third network elements can execute the same subtask.

[0134] It can be understood that after the first network element receives the task request of the terminal device, the first network element determines the plurality of third network elements for executing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, the load and the task completion state of each of the plurality of second network elements, so as to realize the orchestration of the first task. The plurality of third network elements for executing the first task are third network elements in which the model associated with the first task is deployed and which have remaining resources capable of executing the first task or a subtask of the first task based on the load and the task completion state. The action of the first network element determining the plurality of third network elements for executing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, the load and the task completion state of each of the plurality of second network elements can also be regarded as an AI service response made by the first network element to the service request of the terminal device.

[0135] For example, the first network element is an AIMF network element, the second network elements include an s-SU, an n-SU#1 and an n-SU#2, the models deployed by the s-SU include a model 1 and a model 2, the models deployed by the n-SU#1 include the model 2 and a model 3, the models deployed by the n-SU#2 include the model 2, in order to enable the plurality of SUs to complete the execution of the first task in a distributed manner, the first network element splits the first task into a subtask#a and a subtask#b, the model associated with the first task is the model 2, and the load of the s-SU is high, the computing resources of the n-SU#1 and the n-SU#2 are capable of completing the execution of the subtask#a and the subtask#b respectively, then the AIMF network element determines that the n-SU#1 and the n-SU#2 execute the subtask#a and the subtask#b respectively, and the n-SU#1 executes first and the n-SU#2 executes later. It can be seen that after the AIMF network element receives the service request of the terminal device, the AIMF network element can orchestrate the SUs in the serving cell and the SUs in the neighboring cell to execute the first task, so that the n-SU#1 and the n-SU#2 can jointly execute the first task in a distributed manner.

[0136] In an optional implementation, the first network element can also determine the model configuration information of each of the plurality of third network elements based on the execution strategy of the first task. The model configuration information includes the identification of the first model and the parameters of the first model, and the parameters of the first model include at least one of the following: the number of neuron layers of the first model, the neural network width, the connection relationship between layers, the weight of neurons, the activation function of neurons, or the bias in the activation function. The model configuration information of the third network element is used for the third network element to configure the first model, so as to facilitate the third network element to execute the first task based on the configured first model. In addition, the action of the first network element determining the model configuration information of each of the third network elements can be regarded as a process of model initialization configuration of the third network element.

[0137] In an alternative implementation, before determining the plurality of third network elements and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion status of each of the plurality of second network elements, the following steps are further performed: sending task request information to each of the plurality of second network elements, the task request information being used to request to execute the first task, the task request information comprising at least one of the following: an identifier of the first task, a computing power requirement corresponding to the first task, or a first quality of service requirement corresponding to the first task; and receiving task response information from the plurality of second network elements, the task response information being used to respond to whether to execute the first task. The computing power requirement corresponding to the first task refers to a computing power requirement required to execute the first task.

[0138] That is, after receiving the service request of the terminal device, the first network device can send a task request to each of the plurality of second network elements to request the second network element to execute the first task. Thus, each of the plurality of second network elements can determine whether to execute the first task based on at least one of the following: a model deployed by itself, a computing capability of itself, or a remaining computing resource, and the information about the first task carried in the task request. Further, each of the plurality of second network elements feeds back task response information to the first network device to indicate whether to execute the first task.

[0139] Therefore, the first network device determines the plurality of third network elements and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion status of each of the plurality of second network elements, comprising: determining the plurality of third network elements and the execution strategy of the first task based on the task response information of the plurality of second network elements, the model associated with the first task and the model deployment information, load and task completion status of each of the plurality of second network elements. That is, after the first network device requests each of the plurality of second network elements to execute the first task through the task request information, the first network device arranges part or all of the plurality of second network elements to execute the first task based on the task response information fed back by each of the plurality of second network elements, the model associated with the first task and the model deployment information, load and task completion status of each of the plurality of second network elements. In this way, when the first network device arranges the execution of the first task, the task response information fed back by each of the plurality of second network elements is considered, which can improve the reliability of the arrangement of the first task.

[0140] In an optional implementation, each of the second network elements can further send first information to the first network element, and the first information of each of the second network elements includes model deployment information, load and task completion status of the second network element. Correspondingly, the first network element can receive the first information of the plurality of second network elements respectively. This manner can enable the first network element to obtain the model deployment information, load and task completion status of each of the plurality of second network elements, thereby facilitating the first network element to schedule execution of the first task from the plurality of second network elements based on each of the model deployment information, load and task completion status.

[0141] In a possible manner, each of the plurality of second network elements can actively send the first information to the first network element periodically or aperiodically. In another possible manner, the first network element sends request information to each of the plurality of second network elements, and the request information sent to each of the second network elements is used to request the second network element to report model deployment information, load and task completion status. Then, each of the plurality of second network elements sends the first information to the first network element respectively, to report the model deployment information, load and task completion status of itself.

[0142] In a possible manner, each of the plurality of second network elements can directly send the first information to the first network element, or send the first information to the first network element through a CU of an access network device, without limitation.

[0143] In an optional implementation, when the service request of the terminal device includes a first service quality requirement corresponding to the first task, the first network element further determines a second service quality requirement between the i th third network element and the (i+1) th third network element based on the first service quality requirement. The i th third network element is a third network element arranged in the i th position in the order of execution of the first task by the plurality of third network elements, the (i+1) th third network element is a third network element arranged in the (i+1) th position in the order of execution of the first task by the plurality of third network elements, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

[0144] Specifically, when the service request includes a first service quality requirement required for execution of the first task, the first network element further determines a second service quality requirement between the i th third network element and the (i+1) th third network element based on the first service quality requirement, and the computing capability, load, etc. of the i th third network element and the (i+1) th third network element. This manner facilitates the i th third network element to transmit data corresponding to the first task to the (i+1) th third network element based on the second service quality requirement, to meet the first service quality required for execution of the first task and guarantee end-to-end AI service quality. The data corresponding to the first task refers to related data generated by execution of the first task.

[0145] In an alternative implementation, when the first network element obtains the capability information of the terminal device through the service request of the terminal device, the first network element can also consider whether to arrange the terminal device to execute the first task when arranging the execution of the first task. For example, the first network element determines that the terminal device can execute a subtask in the first task by using a model deployed by the terminal device based on the capability information of the terminal device, and then arranges the terminal device to execute the first task in addition to arranging multiple third network elements to execute the first task. In this way, the first network element can also determine the model configuration information of the terminal device, so as to enable the terminal device to configure the model for executing the first task based on the model configuration information.

[0146] S503. The first network element sends the task configuration information to each of the multiple third network elements, and the task configuration information sent to each third network element includes the model configuration information of the third network element and the execution strategy of the first task. Correspondingly, each third network element receives the task configuration information from the first network element.

[0147] The model configuration information of the third network element and the execution strategy of the first task can be referred to S502 and will not be described again.

[0148] It can be understood that after the first network element receives the task request of the terminal device, the first network element arranges multiple third network elements in multiple second network elements to execute the first task, and sends the task configuration information to each third network element to enable each third network element to execute the first task based on the task configuration information.

[0149] For example, the model associated with the first task is model 1, the first network element splits the first task into subtask #a, subtask #b and subtask #c, and the first network element arranges third network element #1, third network element #2 and third network element #3 to execute subtask #a, subtask #b and subtask #c in turn. Then, the first network element sends task configuration information #1, configuration information #2 and configuration information #3 to third network element #1, third network element #2 and third network element #3 respectively, task configuration information #1 includes the configuration information of third network element #1 for configuring model 1 and the execution strategy of the first task, task configuration information #2 includes the configuration information of third network element #2 for configuring model 1 and the execution strategy of the first task, and task configuration information #3 includes the configuration information of third network element #3 for configuring model 1 and the execution strategy of the first task. The execution strategy of the first task includes that third network element #1 executes subtask #a, third network element #2 executes subtask #b in the first task, third network element #3 executes subtask #c in the first task, and the order of third network element #1, third network element #2 and third network element #3 executing the first task.

[0150] In an optional implementation, the first network element further determines the second service quality requirement between the i th third network element and the i+1 th third network element based on the first service quality requirement, and the task configuration information sent by the first network element to the i th third network element further comprises the second service quality requirement between the i th third network element and the i+1 th third network element. In this way, after the i th third network element completes the first task, the i th third network element can transmit the data corresponding to the first task to the i+1 th third network element based on the second service quality requirement, thereby facilitating the multiple third network elements to jointly execute the first task while meeting the first service quality requirement required by the first task, and ensuring the end-to-end AI service quality.

[0151] In another optional implementation, the task configuration information sent by the first network element to the i th third network element further comprises at least one of the following: an identifier of the i+1 th third network element, a data type transmitted between the i th third network element and the i+1 th third network element, and a transmission mode between the i th third network element and the i+1 th third network element.

[0152] In the case where the task configuration information further comprises the identifier of the i+1 th third network element, the i th third network element can pass the data obtained by executing the first task to the i+1 th third network element, so that the i+1 th third network element continues to execute the first task based on the data from the i th third network element. In the case where the task configuration information further comprises the data type transmitted between the i th third network element and the i+1 th third network element, the i th third network element can obtain the data of the data type when executing the first task, so as to transmit the data of the data type to the i+1 th third network element. In the case where the task configuration information further comprises the transmission mode between the i th third network element and the i+1 th third network element, the i th third network element can transmit the data corresponding to the first task to the i+1 th third network element according to the transmission mode.

[0153] In an optional implementation, the first network element further sends first indication information to the i th third network element, and the first indication information sent to the i th third network element is used to instruct the i th third network element to establish a data channel with the i+1 th third network element. In this way, the i th third network element can establish a data channel with the i+1 th third network element, so that the i th third network element transmits the data corresponding to the first task to the i+1 th third network element through the data channel, i.e., transmits the AI data obtained by executing the first task.

[0154] Optionally, the first indication information sent by the first network element to the i th third network element comprises an identifier of the i th third network element and an identifier of the i+1 th third network element, so that the i th third network element can establish a data channel with the i+1 th third network element based on the identifier of the i+1 th third network element.

[0155] Optionally, the first indication information sent by the first network element to the i th third network element further comprises at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of the first model used for executing the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the i th third network element and the i + 1 th third network element.

[0156] The connection relationship of the first model in the plurality of third network elements can be understood as a connection relationship of sub-models in the first model in the plurality of third network elements. For example, the plurality of third network elements include a third network element #1, a third network element #2, and a third network element #3, the third network element #1, the third network element #2, and the third network element #3 execute sub-tasks #a, #b, and #b in the first task in sequence respectively, the first model includes sub-models #a, #b, and #c, and the connection relationship of the first model in the third network element #1, the third network element #2, and the third network element #3 is that the sub-model #a in the third network element #1 is connected with the sub-model #b in the third network element #2, and the sub-model #b in the third network element #2 is connected with the sub-model #c in the third network element #3. In this way, the third network element #1, the third network element #2, and the third network element #3 can determine a data flow direction of data corresponding to the first task based on the connection relationship of the sub-models #a, #b, and #c.

[0157] In an optional implementation, when the first network element orchestrates the terminal device to execute the first task, the first network element can further send task configuration information to the terminal device, the task configuration information comprising model configuration information of the terminal device and an execution strategy of the first task. In this way, the terminal device that is orchestrated can execute the first task based on the task configuration information.

[0158] S504. The fifth network element executes the first task based on the task configuration information.

[0159] The fifth network element is the i th third network element in an execution sequence of the plurality of third network elements for executing the first task.

[0160] It can be understood that after receiving the task configuration information from the first network element, the fifth network element executes the first task based on the first task configuration information. Specifically, the fifth network element executes the first task based on the task configuration information, comprising: configuring a first model based on the model configuration information, the first model being a model associated with the first task; and executing the first task based on the first model and the execution strategy.

[0161] In an alternative implementation, the fifth network element performs the first task based on the first model and the execution strategy, including: receiving first data from the i-1th third network element, the first data being data obtained by the i-1th third network element in performing the first task; performing the first task based on the first data, the first model, and the first task / subtask associated with the fifth network element in the execution strategy, to obtain second data; and sending the second data to the i+1th third network element, so that the i+1th third network element continues to perform the first task based on the second data.

[0162] In an alternative implementation, the fifth network element performs the first task based on the first data, the first model, and the subtask / subtask associated with the fifth network element in the execution strategy, to obtain second data, including: taking the first data as input of the first model, performing the subtask / subtask associated with the fifth network element, and obtaining the second data.

[0163] In an alternative implementation, the task configuration information further includes a second quality of service requirement between the fifth network element and the i+1th third network element, and the fifth network element performs the first task under the condition that the second quality of service requirement is met.

[0164] In an alternative implementation, the task configuration information further includes a data type transmitted between the fifth network element and the i+1th network element, and the fifth network element performs the first task to obtain first data of the data type, so as to send the first data of the data type to the i+1th network element.

[0165] In an alternative implementation, the task configuration information further includes a transmission mode between the fifth network element and the i+1th third network element, and the fifth network element sends the first data to the i+1th third network element based on the transmission mode.

[0166] In an alternative implementation, the fifth network element establishes a data channel with the i+1th third network element upon receiving the first indication information. Thus, the fifth network element sends the first data to the i+1th third network element, including: sending the first data to the i+1th third network element through the data channel established with the i+1th third network element.

[0167] In another alternative implementation, the fifth network element does not receive the first indication information, and the execution strategy of the first task includes an order in which the plurality of third network elements perform the first task. In this case, the fifth network element can also establish a data channel with the i+1th third network element according to the order in which the plurality of third network elements perform the first task, so as to subsequently send the first data to the i+1th third network element through the data channel.

[0168] It can be seen that, in a case where the fifth network element receives the first indication information, the fifth network element can establish a data channel with the (i+1)th third network element based on the first indication information. In a case where the fifth network element does not receive the first indication information, the fifth network element can establish a data channel with the third network element arranged in the i+1th position in the execution sequence based on the order in which the multiple third network elements execute the first task in the execution strategy. Both of the two manners can enable the fifth network element to send the first data to the (i+1)th third network element based on the data channel established with the (i+1)th third network element.

[0169] In an optional implementation, the first network element can further send second indication information to the fourth network element, the second indication information comprising core network information associated with the terminal device, and the fourth network element being a third network element of the multiple third network elements that interacts with the server the data corresponding to the first task. Correspondingly, the fourth network element performs the following steps: receiving the second indication information from the first network element; and establishing a data channel with the server based on the core network information associated with the terminal device.

[0170] The core network information associated with the terminal device can refer to an identifier of a core network network element that provides network services for the terminal device, for example, an identifier of an access and mobility management function (AMF) network element, an identifier of a session management function (SMF) network element, an identifier of a user plane function (UPF) network element, and the like.

[0171] It can be seen that, in the end-network cloud AI collaborative service mode in which the cloud server participates, the first network element can indicate the core network information associated with the terminal device to the fourth network element that interacts with the server the AI data, so that the fourth network element can jointly complete establishment of a data channel with the server, and then the fourth network element can send the data corresponding to the first task to the server through the established data channel.

[0172] In an optional implementation, in a case where the terminal device is configured to execute the first task, the terminal device further executes the first task based on the received task configuration information. The implementation is similar to the implementation of the third network element executing the first task, and thus will not be described herein.

[0173] In the embodiments of the present application, after receiving the service request of the terminal device, the first network element can arrange a plurality of third network elements in the plurality of second network elements to execute the first task and the execution strategy of the first task based on the model deployment information, the load and the task completion state of each second network element in the plurality of second network elements, so as to send the task configuration information including the model configuration information of each third network element in the plurality of third network elements and the execution strategy of the first task to each third network element in the plurality of third network elements, and then each third network element executes the first task based on the received task configuration information. It can be seen that after receiving the service request of the terminal device, the first network element arranges the plurality of third network elements, so that the plurality of third network elements can complete the first task requested by the terminal device in a distributed manner.

[0174] The embodiments of the present application also take the first network element as the AIMF network element deployed on the CN side in the system architecture shown in FIG. 3, and take the second network element as the SU (s-SU) deployed in the service node and the SU (n-SU) deployed in the adjacent node in the system architecture shown in FIG. 3 as examples to illustrate the communication method shown in FIG. 5. FIG. 6 is an interaction diagram of the devices / network elements. As shown in FIG. 6, the interaction of the devices / network elements includes but is not limited to the following steps:

[0175] S601. The s-SU reports the first information, and one or more n-SUs report the first information. The first information includes model deployment information, load and task state information. Correspondingly, the AIMF network element receives the first information of the s-SU and the first information of one or more n-SUs respectively.

[0176] The s-SU and the n-SU are both SUs governed by the AIMF network element. The model deployment information, the load and the task state information can be referred to the description of S502 above, and will not be described again.

[0177] In an optional implementation, the s-SU and the one or more n-SUs can actively report the first information periodically or non-periodically, or can report the first information after receiving the information collection request sent by the AIMF network element. In addition, on the path, the s-SU and the one or more n-SUs can directly report the first information to the AIMF network element, or can report the first information to the AIMF network element through the CU of the local base station, such as that the s-SU reports the first information to the AIMF network element through the CU of the base station in the serving cell, and the n-SU reports the first information to the AIMF network element through the CU of the base station in the adjacent cell corresponding to the n-SU.

[0178] S602. The terminal device sends an AI service request to the AIMF network element. The AI service request is used to request to execute the first task. Correspondingly, the AIMF network element receives the AI service request from the terminal device.

[0179] Optionally, the terminal device can send an AI service request to the AIMF network element through the base station, and the AI service request in this mode can be carried in an RRC message. Optionally, the terminal device can send an AI service request to the AIMF network element through the NAS layer or a new AI control protocol layer.

[0180] It can be understood that in the centralized communication scenario, when the terminal device needs to request the network to perform the first task, the terminal device sends an AI service request to the AIMF network element, so that the AIMF network element can arrange multiple SUs to jointly perform the first task in a distributed manner to implement multi-station joint execution of the first task.

[0181] Optionally, the AI service request can carry the capability information of the terminal device, so that the AIMF network element can arrange whether the terminal device performs the first task based on the capability information of the terminal device. The capability information of the terminal device can be referred to in S501 described above, and will not be described again.

[0182] S603. The AIMF network element arranges the execution of the first task based on the first information of each SU in the multiple SUs.

[0183] The multiple SUs include the s-SU and one or more n-SUs.

[0184] In an optional implementation, the AIMF network element arranges the execution of the first task based on the first information of each SU in the multiple SUs, including: the AIMF network element performs initialization configuration according to the model of the application contract to which the first task belongs, and the model deployment information, load and task completion state of each SU, that is, determines which models are used to execute the first task; based on the model deployment, load and task completion state of each SU, the multiple SUs participating in the execution of the first task and the execution strategy of the multiple SUs executing the first task are determined, and the multiple SUs determined to execute the first task are part or all of the s-SU and one or more n-SUs. For the sake of description, the following service SU represents the SU determined by the AIMF network element to execute the first task.

[0185] The execution strategy of the multiple service SUs executing the first task can be referred to in S502 described above, and will not be described again.

[0186] For example, the first task requested by the terminal device to execute is an AI application with high precision or a certain type of individuality, and the SU in the original service cell of the terminal device retains its individualized model or auxiliary data, and the SU in the current service cell does not have high-precision processing capability or certain type of individualized processing capability. Then, the AIMF network element arranges the SU (i.e., n-SU) in the original service cell to execute the first task.

[0187] In an optional implementation, the AI service request sent by the terminal device to the AIMF network element includes a first quality of service requirement corresponding to the first task, that is, the AI service request includes a first quality of service requirement required for executing the first task. In this way, the AIMF network element can further determine a second quality of service requirement between two service SUs in the execution sequence based on the first quality of service requirement and the load and task completion status of each service SU in the plurality of service SUs. In this way, the two adjacent service SUs in the execution sequence can execute the first task according to the second quality of service requirement, so as to meet the first quality of service requirement required for executing the first task, thereby guaranteeing the quality of service of the AI service and system efficiency.

[0188] For example, the AIMF network element determines that the execution sequence of the first task is s-SU to n-SU#1 and then to n-SU#2. The AIMF network element can determine a second quality of service requirement#a between s-SU and n-SU#1 and a second quality of service requirement#b between n-SU#1 and n-SU#2 based on the first quality of service requirement corresponding to the first task and the load and task completion status of each SU in s-SU, n-SU#1 and n-SU#2. Thus, s-SU can send data corresponding to the first task to n-SU#1 based on the second quality of service requirement#a, and n-SU#1 can send data corresponding to the first task to n-SU#2 based on the second quality of service requirement#b.

[0189] Optionally, the AIMF network element can further determine data flow information of the data corresponding to the first task, that is, determine the data flow direction of the data corresponding to the first task. The data flow direction of the data corresponding to the first task is the same as the execution sequence of the plurality of service SUs executing the first task. For example, s-SU, n-SU#1 and n-SU#2 execute the first task in turn, and the data flow direction of the data corresponding to the first task is s-SU→n-SU#1→n-SU#2.

[0190] Optionally, the AIMF network element can further determine an adjustable range of the model associated with the first task, that is, the adjustable range of the sub-model of the model associated with the first task in the plurality of service SUs. In this way, the plurality of service SUs can dynamically adjust the sub-model to be executed based on their own capabilities.

[0191] Optionally, the AIMF network element can further determine whether the terminal device executes the first task based on the capability information of the terminal device. For example, the AIMF network element determines that the terminal device can execute the first task based on the capability information of the terminal device, and thus arranges the terminal device to execute the first task.

[0192] S604. The AIMF network element sends task configuration information to the plurality of service SUs respectively, the task configuration information comprising model configuration information of the service SUs and an execution strategy of the first task. Correspondingly, the service SUs receive the task configuration information from the AIMF network element respectively.

[0193] The task configuration information can refer to the description in S503 above, and will not be repeated here.

[0194] S605. Each of the plurality of service SUs configures a local model based on the model configuration information in the task configuration information.

[0195] It can be understood that the plurality of service SUs arranged respectively configure local models based on the model configuration information received by themselves, so as to execute the first task using the configured models subsequently.

[0196] S606a. The AIMF network element sends first indication information to the plurality of service SUs respectively, the first indication information sent to each service SU being used to indicate that a data channel is to be established between the service SU and a service SU adjacent to the service SU in execution order. Correspondingly, each service SU performs the following steps: receiving the first indication information from the AIMF network element; and establishing a data channel between the service SU and the service SU adjacent to the service SU in execution order based on the first indication information.

[0197] It can be understood that the AIMF network element also sends first indication information to each service SU, the first indication information being used to indicate that a data channel is to be established between the service SU and a service SU adjacent to the service SU in execution order, so that the service SU establishes a data channel between the service SU and the service SU adjacent to the service SU in execution order based on the first indication information, so as to send data corresponding to the first task to the service SU adjacent to the service SU in execution order through the established data channel subsequently.

[0198] In addition, other implementation manners of the first indication information can refer to the description in S503 above, and will not be repeated here.

[0199] S606b. Each of the plurality of service SUs establishes a data channel between the service SU and a service SU adjacent to the service SU in execution order based on the execution strategy of the first task.

[0200] It can be understood that when the execution strategy of the first task comprises execution orders of the plurality of service SUs, each service SU can actively establish a data channel between the service SU and a service SU adjacent to the service SU in execution order, so as to send data corresponding to the first task to the service SU adjacent to the service SU in execution order through the established data channel subsequently.

[0201] It can be understood that each service SU in the plurality of service SUs performs the above S606a or S606b.

[0202] Optionally, the AIMF network element also sends second indication information to the service SU in the plurality of service SUs that has AI data interaction with the server, and the second indication information is used to indicate the core network information associated with the terminal device. Correspondingly, the service SU that has AI data interaction with the server also performs the following steps: receiving the second indication information from the AIMF network element; and establishing a data channel with the server based on the second indication information. Wherein, the core network information associated with the terminal device can refer to the description in the above S504, and will not be repeated. This way makes the service SU that has AI data interaction with the server can establish a data channel with the server in combination with multiple core network elements (such as AMF network element, SMF network element, UPF network element, etc.) based on the core network information of the terminal device, so as to be able to send data corresponding to the first task to the server based on the established data channel in the subsequent.

[0203] Optionally, when establishing a data channel between two adjacent service SUs in the execution order of the first task, the data channel can be established in the manner of SU-CU-CU-SU. For example, when establishing a data channel between s-SU and n-SU#1, the data channels between sSU-sCU, sCU-nCU#1 and nCU#1-nSU#1 are established in sequence to complete the establishment of the data channel between s-SU and n-SU#1.

[0204] Optionally, when establishing a data channel between two adjacent service SUs in the execution order of the first task, the data channel can be established directly. For example, when establishing a data channel between s-SU and n-SU#1, a direct GTP-U data channel is established between s-SU and n-SU#1.

[0205] Optionally, the service SU can complete the establishment of the SU-CU data channel according to the second quality of service requirement indicated by the AIMF network element, such as air interface QoS.

[0206] Optionally, the base station can complete RRC reconfiguration with the terminal device to establish a data radio bearer (DRB) or a traffic radio bearer (TRB). In addition, the CU of the base station implements mapping and shunting of different bearers to tasks. For each task, the AIMF network element can distinguish data types and QoS according to protocol layer header identification.

[0207] Optionally, after the service SU completes the establishment of each segment of the data channel, it can feed back the complete session information to the AIMF network element (the service SU feeds back directly or through the CU), thereby completing the establishment of the network AI task.

[0208] S607. Each service SU in the plurality of service SUs performs the first task based on the task configuration information.

[0209] The service SU performs the first task based on the task configuration information includes: performing the first task based on the configured local model to obtain data corresponding to the first task.

[0210] Optionally, each service SU also sends the data corresponding to the first task to a service SU adjacent to and after the service SU in the execution order of the first task.

[0211] It can be seen that in the centralized control architecture, after the AIM network element receives the AI service request of the terminal device for requesting to perform the first task, the plurality of SUs can be arranged to perform the first task based on the first information reported by each SU in the s-SU and one or more n-SUs. Thus, each SU in the plurality of SUs arranged to perform the first task can jointly perform the first task based on the task configuration information received by itself, thereby realizing distributed joint execution of the first task.

[0212] The embodiments of the present application also take the first network element as an example of the SU (s-SU) deployed in the service node in the system architecture shown in FIG. 4, and the second network element as an example of the SU (n-SU) deployed in the adjacent node in the system architecture shown in FIG. 4, to illustrate the communication method shown in FIG. 5. FIG. 7 is an interaction diagram of the devices / network elements. As shown in FIG. 7, the interaction of the devices / network elements includes but is not limited to the following steps:

[0213] S701. The s-SU and one or more n-SUs interact with each other first information, and the first information includes model deployment information, load and task completion state.

[0214] The model deployment information, load and task completion state can be referred to the description of S502 above, and will not be repeated here.

[0215] Optionally, the s-SU and one or more n-SUs can periodically or non-periodically interact with each other the first information, which can be active interaction or according to a preset rule.

[0216] S702. The terminal device sends an AI service request to the s-SU, and the AI service request is used to request to perform a first task. Correspondingly, the s-SU receives the AI service request from the terminal device.

[0217] Understandably, in a distributed communication scenario, when the terminal device needs to request the network to perform the first task, the AI service request is sent to the s-SU network element, which can make the s-SU orchestrate one or more n-SUs to jointly perform the first task in a distributed manner to achieve multi-station joint execution of the first task.

[0218] Optionally, the AI service request can carry the capability information of the terminal device, so that the s-SU can use the capability information of the terminal device to determine whether the terminal device performs the first task. The capability information of the terminal device can refer to the description in S501 above, and will not be repeated here.

[0219] S703. The s-SU sends task request information to one or more n-SUs respectively, the task request information being used to request to perform the first task, and the task request information including at least one of the following: an identifier of the first task, a computing power requirement corresponding to the first task, or a first service quality requirement corresponding to the first task. Correspondingly, each SU in the one or more n-SUs respectively receives the task request information from the s-SU.

[0220] Understandably, limited by the deployed model capability, computing power and load situation of the s-SU, the s-SU initiates a request (AI service request) for distributed AI application execution to the one or more n-SUs, which can carry the identifier of the first task, the computing power requirement corresponding to the first task, or the first service quality requirement corresponding to the first task, etc., so as to complete the AI task requested by the terminal device by means of the capability of the one or more n-SUs.

[0221] Optionally, the s-SU and the one or more n-SUs can directly interact with each other, or can interact with each other through the CU of the local base station.

[0222] S704. The one or more n-SUs respectively send task request responses to the s-SU, the task request responses being used to indicate whether to perform the first task.

[0223] Understandably, after the one or more n-SUs receive the task request information from the s-SU, based on the model information, load and task completion state deployed by themselves, they determine whether to participate in the execution of the first task, and feed back whether to participate in the execution of the first task to the s-SU through the task response information, so that the s-SU orchestrates the execution of the first task.

[0224] S705. The s-SU orchestrates the execution of the first task based on the task request response of each n-SU in the one or more n-SUs and the first information.

[0225] Specifically, the s-SU determines the one or more n-SUs to execute the first task and the execution strategy of executing the first task based on the task request response, the model deployment information, the load and the task completion status of each of the one or more n-SUs, and the model associated with the first task.

[0226] For ease of description, the following uses a service SU to represent the one or more n-SUs determined by the s-SU to execute the first task. The service SU is the n-SU indicated by the task request response to execute the first task, and determined by the s-SU to execute the first task.

[0227] Optionally, when the AI service request carries the capability information of the terminal device, the s-SU can further determine whether the terminal device executes the first task based on the capability information of the terminal device. For example, the s-SU further determines that the terminal device can execute the first task based on the capability information of the terminal device, and can further arrange the terminal device to execute the first task.

[0228] S706. The s-SU sends task configuration information to the plurality of service SUs respectively, and the task configuration information includes the model configuration information of the service SU and the execution strategy of the first task. Correspondingly, each service SU receives the task configuration information from the s-SU.

[0229] The model configuration information of the SU and the execution strategy of the first task can refer to the description of S502 above, and will not be described again.

[0230] S707. Each service SU in the plurality of service SUs configures a local model based on the model configuration information in the task configuration information.

[0231] S708a. The s-SU sends first indication information to the plurality of service SUs respectively, and the first indication information sent to each service SU is used to indicate that a data channel is established between the service SU and the service SU adjacent to the service SU in the execution order. Correspondingly, each service SU performs the following steps: receiving the first indication information from the s-SU network element; based on the first indication information, establishing a data channel between the service SU and the service SU adjacent to the service SU in the execution order.

[0232] S708b. Each service SU in the plurality of service SUs establishes a data channel between the service SU and the service SU adjacent to the service SU in the execution order based on the execution strategy of the first task.

[0233] Optionally, the s-SU also sends second indication information to the service SUs in the plurality of service SUs that have AI data interaction with the server, the second indication information being used to indicate the core network information associated with the terminal device. Correspondingly, the service SUs that have AI data interaction with the server further perform the following steps: receiving the second indication information from the AIMF network element; and establishing a data channel with the server based on the second indication information. Wherein, the core network information associated with the terminal device can refer to the description of S504 above, and will not be repeated. This way makes the service SUs that have AI data interaction with the server can establish a data channel with the server based on the core network information of the terminal device, in conjunction with multiple core network elements, so as to be able to send data corresponding to the first task to the server based on the established data channel subsequently. For example, the s-CU carries the core network information associated with the terminal device through an Xn message or in a data tunnel establishment request to assist the channel establishment between the nCU-UPF, and then establish a data channel with the server.

[0234] S709. Each service SU in the plurality of service SUs performs the first task based on the task configuration information.

[0235] Wherein, the implementation manners of S708a, S708b and S709 can refer to the implementation manners of S606a, S606b and S607 respectively, and will not be repeated.

[0236] It can be seen that in the distributed architecture, after the s-SU receives the AI service request of the terminal device for requesting to perform the first task, the s-SU can request one or more n-SUs to perform the first task respectively, so as to arrange part of the n-SUs to perform the first task based on the task request response fed back by each n-SU of the one or more n-SUs and the model deployment information, load and task completion state of each n-SU. Thus, each n-SU in the arranged plurality of n-SUs can perform the first task based on the task configuration information received by itself, realizing the distributed joint execution of the first task by the plurality of SUs. Compared with the communication method shown in FIG. 6, the SUs can interact with each other, without the need for a central node to control uniformly, so as to reduce the signaling overhead and interaction cost required for decision-making.

[0237] For the technical solutions described above, the corresponding device implementation scheme is further described below.

[0238] In order to realize the functions in the method provided by the embodiments of the present application, the first network element and the fifth network element can include hardware structures and / or software modules to realize the above-mentioned functions in the form of hardware structures, software modules, or hardware structures plus software modules. Whether a certain function in the above-mentioned functions is executed in the form of hardware structure, software module, or hardware structure plus software module depends on the specific application and design constraints of the technical solution.

[0239] As shown in FIG. 8, the embodiment of the present application provides a communication apparatus 800. The communication apparatus 800 can be a component (for example, an integrated circuit, a chip, etc.) of the first network element, or a component (for example, an integrated circuit, a chip, etc.) of the fifth network element. The communication apparatus 800 can also be another communication unit for implementing the method in the method embodiment of the present application. The communication apparatus 800 can include a communication unit 801 and a processing unit 802. Optionally, it can also include a storage unit 803.

[0240] In a possible design, one or more units in FIG. 8 can be implemented by one or more processors, or by one or more processors and memories; or by one or more processors and transceivers; or by one or more processors, memories and transceivers, and the embodiment of the present application is not limited to this. The processor, memory and transceiver can be separately arranged, or integrated.

[0241] The communication apparatus 800 has the function of the first network element or the function of the fifth network element described in the embodiment of the present application. For example, the communication apparatus 800 includes a module or unit or means corresponding to the first network element involved step in the above-mentioned method embodiments executed by the first network element, and the function or unit or means can be implemented by software, or by hardware, or by executing corresponding software by hardware, or by a combination of software and hardware. For details, further reference can be made to the corresponding description in the foregoing method embodiments.

[0242] In a possible design, the communication apparatus 800 can include a processing unit 802 and a communication unit 801, and the apparatus is applied to the first network element.

[0243] The communication unit 801 is configured to receive a service request of a terminal device, and the service request is used to request to execute a first task.

[0244] The processing unit 802 is configured to determine a plurality of third network elements for executing the first task and an execution strategy of the first task based on a model associated with the first task and model deployment information, load and task completion state of each of a plurality of second network elements, and the plurality of third network elements are part or all of the plurality of second network elements.

[0245] The communication unit 801 is further configured to send task configuration information to each of the plurality of third network elements, and the task configuration information sent to each of the third network elements includes model configuration information of the third network element and the execution strategy of the first task.

[0246] In an optional implementation, the execution strategy of the first task comprises at least one of the following: an execution sequence of the plurality of third network elements for the first task, and a subtask executed by each of the plurality of third network elements; the subtask is a partial task in the first task.

[0247] In an optional implementation, the plurality of second network elements comprises a second network element of a serving cell and a second network element of a neighboring cell; or the plurality of second network elements are second network elements of neighboring cells.

[0248] In an optional implementation, before determining the plurality of third network elements and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load, and task completion status of each of the plurality of second network elements, the processing unit 802 is further configured to: send task request information to each of the plurality of second network elements, the task request information being used to request execution of the first task, and the task request information comprising at least one of the following: an identifier of the first task, a computing power requirement corresponding to the first task, or a first service quality requirement corresponding to the first task; and receive task response information of the plurality of second network elements, the task response information being used to respond to whether to execute the first task; and determine the plurality of third network elements and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load, and task completion status of each of the plurality of second network elements, specifically by determining the plurality of third network elements and the execution strategy of the first task based on the task response information of the plurality of second network elements, the model associated with the first task, and the model deployment information, load, and task completion status of each of the plurality of second network elements.

[0249] In an optional implementation, the service request comprises a first service quality requirement corresponding to the first task, and the execution strategy of the first task comprises an execution sequence of the plurality of third network elements for the first task; the task configuration information sent to the i th third network element further comprises a second service quality requirement between the i th third network element and an (i+1) th third network element, the second service quality requirement being determined based on the first service quality requirement; the i th third network element is a third network element arranged in the i th position in the execution sequence of the plurality of third network elements for the first task, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

[0250] In an alternative implementation, the task configuration information sent to the i-th third network element further includes at least one of the following: an identifier of the (i+1)-th third network element, a data type transmitted between the i-th third network element and the (i+1)-th third network element, and a transmission mode between the i-th third network element and the (i+1)-th third network element.

[0251] In an alternative implementation, the communication unit 801 is further configured to receive the first information of each second network element, the first information of each second network element including model deployment information, load, and task completion status of the second network element.

[0252] In an alternative implementation, the communication unit 801 is further configured to send first indication information to an i-th third network element, the first indication information sent to the i-th third network element being used to instruct the i-th third network element to establish a data channel with a (i+1)-th third network element, the i-th third network element being a third network element arranged in an i-th position in an order in which the plurality of third network elements execute the first task, i being a positive integer, and i+1 being less than or equal to a number of the plurality of third network elements.

[0253] In an alternative implementation, the first indication information sent to the i-th third network element includes an identifier of the i-th third network element and an identifier of the (i+1)-th third network element.

[0254] In an alternative implementation, the first indication information sent to the i-th third network element further includes at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of a first model used to execute the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the i-th third network element and the (i+1)-th third network element.

[0255] In an alternative implementation, the communication unit 801 is further configured to send second indication information to a fourth network element, the second indication information including core network information associated with the terminal device, the fourth network element being a third network element of the plurality of third network elements that interacts with a server to transmit data corresponding to the first task.

[0256] In another possible design, the communication apparatus 800 can include a processing unit 802 and a communication unit 801, and the apparatus is applied to a fifth network element.

[0257] The communication unit 801 is configured to receive task configuration information from a first network element, the task configuration information including model configuration information and an execution strategy of a first task, the first task being a task requested to be executed by a terminal device.

[0258] The processing unit 802 is configured to execute the first task based on the task configuration information.

[0259] In an optional implementation, the execution strategy of the first task includes at least one of the following: an execution sequence of the plurality of third network elements, and a subtask executed by each of the plurality of third network elements; the fifth network element is one of the plurality of third network elements, and the subtask is a partial task in the first task.

[0260] In an optional implementation, the fifth network element is an i-th network element in an execution sequence of the plurality of third network elements; the task configuration information further includes a second quality of service requirement between the fifth network element and an i+1-th network element, the i+1-th network element is an i+1-th network element in the execution sequence of the plurality of third network elements; i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

[0261] In an optional implementation, the task configuration information further includes at least one of the following: an identifier of the i+1-th network element, a data type transmitted between the fifth network element and the i+1-th network element, and a transmission mode between the fifth network element and the i+1-th network element.

[0262] In an optional implementation, the communication unit 801 is further configured to send first information, the first information including model deployment information, load, and a task completion state of the fifth network element.

[0263] In an optional implementation, the processing unit 802 is further configured to: receive first indication information, the first indication information being used to indicate that the fifth network element and an i+1-th network element establish a data channel; based on the first indication information, establish a data channel with the i+1-th network element; wherein the fifth network element is an i-th network element in an execution sequence of a plurality of third network elements, the i+1-th network element is an i+1-th network element in the execution sequence of the plurality of third network elements; i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

[0264] In an optional implementation, the first indication information includes an identifier of the fifth network element and an identifier of the i+1-th network element.

[0265] In an optional implementation, the first indication information further includes at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of a first model used for executing the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the fifth network element and the i+1th third network element.

[0266] In an optional implementation, the execution strategy of the first task includes an order of the plurality of third network elements executing the first task, and the processing unit 802 is further configured to establish a data channel with an i+1th third network element according to the order of the plurality of third network elements executing the first task; wherein the fifth network element is a third network element arranged at an i-th position in the order of the plurality of third network elements executing the first task, and the i+1th third network element is a third network element arranged at an i+1th position in the order of the plurality of third network elements executing the first task; the i is a positive integer, and the i+1 is less than or equal to a number of the plurality of third network elements.

[0267] In an optional implementation, the processing unit 802 is further configured to receive second indication information, the second indication information including core network information associated with the terminal device; and establish a data channel with a server based on the core network information associated with the terminal device.

[0268] Embodiments of the present application and the above-described method embodiments are based on the same concept and bring the same technical effects. For specific principles, refer to the description of the above-described embodiments, which will not be repeated here.

[0269] Embodiments of the present application also provide a communication apparatus 900, and FIG. 9 is a structural schematic diagram of the communication apparatus 900. The communication apparatus 900 can be a first network element, or a chip, chip system, or processor supporting the first network element to implement the above-described method; or the communication apparatus 900 can be a fifth network element, or a chip, chip system, or processor supporting the fifth network element to implement the above-described method. The apparatus can be used to implement the method described in the above-described method embodiments, and specific implementation can be referred to the description in the above-described method embodiments.

[0270] The communication apparatus 900 can include one or more processors 901. The processor 901 can be a general processor or a special purpose processor, etc. For example, it can be a baseband processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, and the CPU can be used to control the communication apparatus (e.g., a base station, a baseband chip, a terminal, a terminal chip, a DU or a CU, etc.), execute software programs, and process data of the software programs.

[0271] Optionally, the communication apparatus 900 can include one or more memories 902, which can store instructions 904 executable by the processor 901 to cause the communication apparatus 900 to perform the methods described in the above method embodiments. Optionally, the memory 902 can also store data. The processor 901 and the memory 902 can be separately arranged or integrated together.

[0272] Optionally, the communication apparatus 900 can further include a transceiver 905, an antenna 906. The transceiver 905 can be referred to as a transceiving unit, a transceiver, or a transceiving circuit, etc., and is used to implement the transceiving function. The transceiver 905 can include a receiver and a transmitter. The receiver can be referred to as a receiver or a receiving circuit, etc., and is used to implement the receiving function. The transmitter can be referred to as a transmitter or a transmitting circuit, etc., and is used to implement the transmitting function.

[0273] In a possible design, the communication apparatus 900 can be applied to the first network element. Specifically, the transceiver 905 is configured to perform S501 and S503 in the communication method described in FIG. 5, and the processor 901 is configured to perform S502 in the communication method described in FIG. 5.

[0274] In another possible design, the communication apparatus 900 can be applied to the fifth network element. Specifically, the transceiver 905 is configured to perform S503 in the communication method described in FIG. 5, and the processor 901 is configured to perform S504 in the communication method described in FIG. 5.

[0275] Optionally, the processor 901 can store instructions 903, which are executable on the processor 901 to cause the communication apparatus 900 to perform the methods described in the above method embodiments. The instructions 903 can be fixed in the processor 901, and in this case, the processor 901 can be implemented by hardware.

[0276] The embodiments of the present application and the method embodiments shown in the communication method described in FIG. 5 are based on the same concept, and the technical effects brought by the embodiments are the same. For specific principles, refer to the description of the embodiments of the communication method described in FIG. 5, and details are not repeated.

[0277] The embodiments of the present application also provide a communication system, which includes a first network element and a plurality of second network elements. In another possible design, the system can further include other devices / functional network elements that interact with the first network element and the plurality of second network elements.

[0278] The embodiments of the present application also provide a computer readable storage medium for storing computer software instructions, which, when executed by a communication device, implement the functions of any of the method embodiments.

[0279] The embodiments of the present application also provide a computer program product for storing computer software instructions, which, when executed by a communication device, implement the functions of any of the method embodiments.

[0280] The embodiments of the present application also provide a computer program, which, when executed on a computer, implements the functions of any of the method embodiments.

[0281] The terms "first" and "second" and the like in the description, claims, and drawings of the embodiments of the present application are used to distinguish different objects, and are not used to describe a specific order. "First", "second", and the like are only used for description purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second", and the like can explicitly or implicitly include one or more of the features. In the description of the embodiments, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0282] In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a list of steps or units is not limited to the listed steps or units, but can optionally include other steps or units not listed or can optionally include other steps or units inherent to the process, method, product, or device.

[0283] In the embodiments of the present application, the phrase "embodiment" means that the specific features, structures, or properties described in conjunction with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily mean the same embodiment, nor is it a separate or alternative embodiment independent of or to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0284] In the embodiments of the present application, "at least one" means one or more, "multiple" means two or more, and "and / or" is used to describe the relationship between associated objects, indicating that there can be three relationships, for example, "A and / or B" can represent three cases: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after it. "At least one of the following" or similar expressions means any combination of these items, including single or multiple combinations. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0285] In the embodiments of the present application, the words "exemplary" or "for example" are used to mean serving as an example or illustration. Any embodiment or design presented as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of "exemplary" or "for example" is intended to present concepts in a concrete manner, facilitating understanding.

[0286] In the above embodiments, all or part can be realized by software, hardware, firmware, or any combination thereof. When realized by software, all or part can be realized in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another, for example, the computer instructions can be transferred from one website, computer, server or data center to another through wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available media can be magnetic media (such as floppy disk, hard disk, magnetic tape), optical media (such as high-density digital video disc (digital video disc, DVD)), or semiconductor media (such as SSD), etc.

[0287] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method is applied to a first network element, and the method comprises: receiving a service request of a terminal device, the service request being used for requesting to perform a first task; determining a plurality of third network elements for performing the first task and an execution strategy of the first task based on a model associated with the first task and model deployment information, load and task completion status of each second network element in a plurality of second network elements, the plurality of third network elements being part or all of the plurality of second network elements; sending task configuration information to each third network element in the plurality of third network elements, the task configuration information sent to each third network element comprising model configuration information of the third network element and the execution strategy of the first task.

2. The method of claim 1, wherein the execution strategy of the first task comprises at least one of the following: an order in which the plurality of third network elements perform the first task, and a subtask performed by each third network element in the plurality of third network elements; the subtask is a part of the first task.

3. The method of claim 1 or 2, wherein the plurality of second network elements comprise second network elements of a serving cell and second network elements of a neighbor cell; or the plurality of second network elements are second network elements of a neighbor cell.

4. The method according to any one of claims 1 to 3, characterized in that, Before the determining of the plurality of third network elements for performing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion status of each second network element in the plurality of second network elements, the method further comprises: sending task request information to each second network element, the task request information being used for requesting to perform the first task, the task request information comprising at least one of the following: an identifier of the first task, a computing power requirement corresponding to the first task, or a first quality of service requirement corresponding to the first task; receiving task response information of the plurality of second network elements, the task response information being used for responding to whether to perform the first task; the determining of the plurality of third network elements for performing the first task and the execution strategy of the first task based on the model associated with the first task and the model deployment information, load and task completion status of each second network element in the plurality of second network elements comprises: determining the plurality of third network elements for performing the first task and the execution strategy of the first task based on the task response information of the plurality of second network elements, the model associated with the first task and the model deployment information, load and task completion status of each second network element.

5. The method according to any one of claims 1 to 4, characterized in that, the service request comprises a first quality of service requirement corresponding to the first task, and the execution strategy of the first task comprises an order in which the plurality of third network elements perform the first task; the task configuration information sent to the i-th third network element further comprises a second quality of service requirement between the i-th third network element and the i+1-th third network element, the second quality of service requirement being determined based on the first quality of service requirement; The ith third network element is a third network element arranged in the ith position in the sequence in which the plurality of third network elements perform the first task, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

6. The method of claim 5, wherein, The task configuration information sent to the ith third network element further includes at least one of the following: an identifier of the i+1th third network element, a data type transmitted between the ith third network element and the i+1th third network element, and a transmission mode between the ith third network element and the i+1th third network element.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: receiving first information of each second network element, the first information of each second network element including model deployment information, load, and task completion status of the second network element.

8. The method according to any one of claims 1 to 7, characterized in that, The method further includes: sending first indication information to the ith third network element, the first indication information sent to the ith third network element being used to instruct the ith third network element to establish a data channel with the i+1th third network element; The ith third network element is a third network element arranged in the ith position in the sequence in which the plurality of third network elements perform the first task, i is a positive integer, and i+1 is less than or equal to the number of the plurality of third network elements.

9. The method of claim 8, wherein, The first indication information sent to the ith third network element includes an identifier of the ith third network element and an identifier of the i+1th third network element.

10. The method of claim 8 or 9, wherein, The first indication information sent to the ith third network element further includes at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of a first model used to perform the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the ith third network element and the i+1th third network element.

11. The method according to any one of claims 1 to 10, characterized in that, The method further includes: sending second indication information to a fourth network element, the second indication information including core network information associated with the terminal device; The fourth network element is a third network element of the plurality of third network elements that interacts with a server to transmit data corresponding to the first task.

12. A communication method, comprising: The method is applied to a fifth network element, and the method includes: receiving task configuration information from a first network element, the task configuration information including model configuration information and an execution strategy of a first task, the first task being a task requested to be performed by a terminal device; performing the first task based on the task configuration information.

13. The method of claim 12, wherein, The execution strategy of the first task includes at least one of the following: a sequence in which a plurality of third network elements perform the first task, and a subtask performed by each third network element of the plurality of third network elements; The fifth network element is one of the plurality of third network elements, and the subtask is a part of the first task.

14. The method according to claim 12 or 13, characterized in that, The fifth network element is a third network element arranged in the ith position in the sequence in which the plurality of third network elements perform the first task. The task configuration information further comprises a second quality of service requirement between the fifth network element and an i+1th third network element, the i+1th third network element being a third network element arranged in an i+1th position in a sequence in which the plurality of third network elements execute the first task; The i is a positive integer, and the i+1 is less than or equal to a quantity of the plurality of third network elements.

15. The method of claim 14, wherein, The task configuration information further comprises at least one of the following: an identifier of the i+1th third network element, a data type transmitted between the fifth network element and the i+1th third network element, and a transmission mode between the fifth network element and the i+1th third network element.

16. The method according to any one of claims 12 to 15, characterized in that, The method further comprises: sending first information, the first information comprising model deployment information, a load, and a task completion state of the fifth network element.

17. The method according to any one of claims 12 to 16, characterized in that, The method further comprises: receiving first indication information, the first indication information being used to indicate that the fifth network element and an i+1th third network element establish a data channel; based on the first indication information, establishing the data channel with the i+1th third network element; The fifth network element is a third network element arranged in an i th position in a sequence in which the plurality of third network elements execute the first task, and the i+1th third network element is a third network element arranged in an i+1th position in the sequence in which the plurality of third network elements execute the first task. The i is a positive integer, and the i+1 is less than or equal to a quantity of the plurality of third network elements.

18. The method of claim 17, wherein The first indication information comprises an identifier of the fifth network element and an identifier of the i+1th third network element.

19. The method of claim 17 or 18, wherein The first indication information further comprises at least one of the following: an identifier of the first task, an identifier of the terminal device, an identifier of a first model used to execute the first task, a connection relationship of the first model in the plurality of third network elements, or a transmission protocol between the fifth network element and the i+1th third network element.

20. The method according to any one of claims 12 to 16, characterized in that, The execution strategy of the first task comprises a sequence in which the plurality of third network elements execute the first task, and the method further comprises: based on the sequence in which the plurality of third network elements execute the first task, establishing the data channel with an i+1th third network element; The fifth network element is a third network element arranged in an i th position in a sequence in which the plurality of third network elements execute the first task, and the i+1th third network element is a third network element arranged in an i+1th position in the sequence in which the plurality of third network elements execute the first task. The i is a positive integer, and the i+1 is less than or equal to a quantity of the plurality of third network elements.

21. The method according to any one of claims 12 to 20, characterized in that, The method further comprises: receiving second indication information, the second indication information comprising core network information associated with the terminal device; based on the core network information associated with the terminal device, establishing a data channel with a server.

22. A communications device, characterized by The communication apparatus comprises a module for performing the method of any one of claims 1 to 11, or a module for performing the method of any one of claims 12 to 21.

23. A communications device, characterized by The communication device comprises a processor configured to perform the method according to any one of claims 1 to 11, or configured to perform the method according to any one of claims 12 to 21.

24. A computer-readable storage medium, characterized in that, The computer readable storage medium stores instructions which, when executed by a communication device, implement the method according to any one of claims 1 to 11, or implement the method according to any one of claims 12 to 21.

25. A computer program product comprising instructions, wherein: The instructions, when executed on a communication device, implement the method according to any one of claims 1 to 11, or implement the method according to any one of claims 12 to 21.

Images