AI task indication method, communication device and system

Abstract

The invention provides an AI task indication method, a communication device and a system, which can be applied to a scene in which AI is combined with a wireless network. The method comprises the steps that a control node obtains an AI task and determines arrangement information of at least one network node for the AI task, and the arrangement information of each network node can indicate operation provided when each network node participates in execution of the AI task; and the control node sends arrangement information to part or all of the at least one network node. By means of the mode, the network nodes in the wireless network can execute the AI task, fusion of the AI and the wireless network is achieved, the control nodes are arranged in a unified mode, and the overall efficiency can be improved.

Description

AI task instruction method, communication device and system Technical Field

[0001] The present application relates to the field of wireless communications, specifically, to wireless communication technology using intelligent networks, and more particularly to a method, communication device, and system for AI task indication. Background Art

[0002] To meet the vision of intelligent and inclusive future, intelligence will further evolve at the wireless network architecture level. Artificial intelligence (AI) will be further integrated with wireless networks, achieving both inherent network intelligence and terminal intelligence, thereby addressing potential new demands and scenarios. How to achieve the integration of AI and wireless networks is an urgent issue that needs to be addressed.

[0003] Summary of the Invention

[0004] The present application provides a method, communication device, and system for AI task indication. By having a control node determine scheduling information for an AI task and indicate the scheduling information, AI tasks can be executed through network nodes in a wireless network, thereby realizing the integration of AI and wireless networks.

[0005] In a first aspect, a method for AI task indication is provided, which can be executed by a control node. The control node can be a device, or a chip (system) or circuit for a device, which is not limited in this application.

[0006] The method may include: a control node determining first orchestration information for an AI task, the first orchestration information instructing a first network node to perform a first task of the AI ​​task; and the control node sending the first orchestration information to the first network node.

[0007] Based on the above technical solution, a control node can determine the orchestration information of network nodes for AI tasks and send this orchestration information to the network nodes, which can then perform corresponding operations based on this orchestration information. This not only enables network nodes in the wireless network to execute AI tasks, achieving the integration of AI and wireless networks, but also allows the control node to perform unified orchestration, which can improve overall efficiency.

[0008] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the control node determines second orchestration information for the AI ​​task, the second orchestration information instructing the second network node to perform the second task of the AI ​​task; the control node sends the second orchestration information to the first network node, or the control node sends the second orchestration information to the second network node.

[0009] Based on the above technical solution, the control node determines the orchestration information of multiple network nodes for the AI ​​task, which can improve global efficiency. In addition, the control node can send the orchestration information of each network node to a certain network node (such as the first network node), reducing the signaling overhead caused by the control node sending the orchestration information to each network node. Alternatively, the control node can also send the orchestration information of each network node to each network node separately, which can reduce the signaling overhead caused by transmitting the orchestration information between network nodes.

[0010] In combination with the first aspect, in certain implementations of the first aspect, the method further includes: the control node determines second orchestration information for the AI ​​task, the second orchestration information instructing the second network node to perform the second task of the AI ​​task; the control node sends the first orchestration information and the second orchestration information to the second network node; the control node sends the first orchestration information to the first network node, including: the control node sends the first orchestration information and the second orchestration information to the first network node.

[0011] Based on the above technical solution, the control node determines the orchestration information of multiple network nodes for the AI ​​task, which can improve overall efficiency. In addition, the control node can send the orchestration information of all network nodes to each network node, which can reduce the overhead caused by the control node selecting the orchestration information of each network node.

[0012] In combination with the first aspect, in certain implementations of the first aspect, the first network node is the first network node to participate in executing the AI ​​task.

[0013] In combination with the first aspect, in some implementations of the first aspect, the first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for performing the first task, and an exit condition for the first network node to perform the first task.

[0014] In combination with the first aspect, in certain implementations of the first aspect, the control node determines first orchestration information for the AI ​​task, including: the control node determines the first orchestration information for the AI ​​task based on the AI ​​capability of the first network node.

[0015] Based on the above technical solution, the control node can determine the orchestration information of the network node based on the AI ​​capability of the network node. In this way, the orchestration information determined by the control node can match the AI ​​capability of each network node, reducing the probability that the network node cannot perform AI tasks.

[0016] In combination with the first aspect, in some implementations of the first aspect, the method further includes: the control node receiving response information from the first network node, where the response information indicates whether the first network node agrees with the first orchestration information.

[0017] Based on the above technical solution, the network node can also send a response to the control node whether it agrees with the orchestration information. This makes it easier for the control node to know whether the network node agrees with the orchestration information, and then determine whether to issue the AI ​​task.

[0018] In a second aspect, a method for AI task indication is provided, which can be executed by a network node. The network node can be a device, or a chip (system) or circuit for a device, which is not limited in this application. The following description takes the first network node as an example.

[0019] The method may include: a first network node receiving first orchestration information from a control node, the first orchestration information instructing the first network node to execute a first task of an AI task; and the first network node executing the first task according to the first orchestration information.

[0020] In combination with the second aspect, in certain implementations of the second aspect, the first network node receives first orchestration information from the control node, including: the first network node receives the first orchestration information and second orchestration information from the control node, the second orchestration information instructing the second network node to perform the second task of the AI ​​task; the method also includes: the first network node sends the second orchestration information to the second network node.

[0021] In combination with the second aspect, in some implementations of the second aspect, the first network node sending the second orchestration information to the second network node includes: the first network node sending the processing result of the first task and the second orchestration information to the second network node.

[0022] In combination with the second aspect, in certain implementations of the second aspect, the first network node is the first network node to participate in executing the AI ​​task.

[0023] In combination with the second aspect, in some implementations of the second aspect, the first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for performing the first task, and an exit condition for the first network node to perform the first task.

[0024] In combination with the second aspect, in some implementations of the second aspect, the method further includes: the first network node sending the AI ​​capability of the first network node to the control node.

[0025] In combination with the second aspect, in some implementations of the second aspect, the method further includes: the first network node sending response information to the control node, where the response information indicates whether the first network node agrees with the first orchestration information.

[0026] In combination with the second aspect, in certain implementations of the second aspect, the method further includes: the first network node sends the first task or part of the first task to at least one terminal device; or, the first network node sends the first task or part of the first task to the second network node, and the second network node is at least one network node participating in executing the AI ​​task.

[0027] Based on the above technical solution, the network node can schedule other network nodes (such as the second network node) or terminal devices to collaboratively perform AI tasks. This can perform AI tasks by utilizing idle computing power, which can not only improve resource utilization but also increase flexibility.

[0028] In combination with the second aspect, in certain implementations of the second aspect, at least one terminal device is in a preset state.

[0029] Based on the above technical solution, by defining different states for terminals, it is possible to facilitate network nodes to determine whether a terminal can participate in AI tasks based on the terminal's state. For example, a network node can send an AI task to a terminal in a preset state, that is, the AI ​​in the preset state can participate in the AI ​​task.

[0030] In combination with the second aspect, in certain implementations of the second aspect, before the first network node sends the first task or part of the first task to at least one terminal device, the method also includes: the first network node sends notification information to at least one terminal device, and the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0031] The beneficial effects of the second aspect and each possible design can be referred to the relevant description of the first aspect and will not be repeated here.

[0032] In a third aspect, a method for AI task indication is provided, which can be executed by a network node. The network node can be a device, or a chip (system) or circuit for a device, which is not limited in this application. The following description takes the first network node as an example.

[0033] The method may include: the first network node sending a processing result and target state information of a first task of the AI ​​task to the second network node, where the target state information is used to indicate a target result of the AI ​​task.

[0034] For example, the processing result and target state information of the first task may implicitly indicate that the second network node participates in executing the AI ​​task, such as the second network node executing the second task of the AI ​​task.

[0035] Based on the above technical solution, network nodes can collaborate to perform AI tasks, and network nodes can determine whether to participate in the execution of AI tasks based on current processing results and target status information, reducing the signaling overhead caused by instructing network nodes to participate in the execution of AI tasks.

[0036] In combination with the third aspect, in certain implementations of the third aspect, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node, including: based on the AI ​​capability of the second network node, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node.

[0037] Based on the above technical solution, the first network node can determine whether to send the processing result and target state information of the first AI task to the second network node based on the second network node's AI capabilities. In other words, it can determine whether the second network node should participate in executing the AI ​​task. This can reduce the probability that the second network node will be unable to participate in executing the AI ​​task.

[0038] In conjunction with the third aspect, in certain implementations of the third aspect, the method further includes: the first network node sending first request information to the control node or the second network node, the first request information requesting the AI ​​capability of the second network node; and the first network node receiving response information to the first request information, the response information to the first request information indicating the AI ​​capability of the second network node.

[0039] In combination with the third aspect, in certain implementations of the third aspect, before the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node, the method also includes: the first network node sends a second request information to the second network node, and the second request information requests the second network node to collaborate in executing the AI ​​task.

[0040] Based on the above technical solution, when the first network node determines that the second network node agrees to collaborate in executing the AI ​​task, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node, thereby reducing the probability that the second network node will not be able to participate in executing the AI ​​task.

[0041] In combination with the third aspect, in certain implementations of the third aspect, the processing result of the first task represents current status information of the AI ​​task.

[0042] Based on the above technical solution, the current state information and target state information of the AI ​​task may instruct the second network node to participate in executing the AI ​​task, such as executing the second task of the AI ​​task.

[0043] In combination with the third aspect, in certain implementations of the third aspect, the method further includes: the first network node also sends area information to the second network node, and the area information is used by the second network node to determine the network node that collaborates to perform the AI ​​task.

[0044] In combination with the third aspect, in certain implementations of the third aspect, the method further includes: the first network node sending the first task or a portion of the first task to at least one terminal device.

[0045] Based on the above technical solution, network nodes can schedule terminal devices to collaboratively execute AI tasks. This can utilize idle computing power to execute AI tasks, which can not only improve resource utilization but also increase flexibility.

[0046] In combination with the third aspect, in certain implementations of the third aspect, at least one terminal device is in a preset state.

[0047] Based on the above technical solution, by defining different states for terminals, it is possible to facilitate network nodes to determine whether a terminal can participate in AI tasks based on the terminal's state. For example, a network node can send an AI task to a terminal in a preset state, that is, the AI ​​in the preset state can participate in the AI ​​task.

[0048] In combination with the third aspect, in certain implementations of the third aspect, before the first network node sends the first task or part of the first task to at least one terminal device, the method also includes: the first network node sends notification information to at least one terminal device, and the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0049] In a fourth aspect, a method for AI task indication is provided, which can be performed by a network node. The network node can be a device, or a chip (system) or circuit for a device, which is not limited in this application. The following description takes the second network node as an example.

[0050] The method may include: a second network node receiving a processing result and target state information of a first task of an AI task from a first network node, where the target state information is used to indicate a target result of the AI ​​task; and the second network node executing a second task of the AI ​​task based on the processing result and target state information of the first task.

[0051] In combination with the fourth aspect, in certain implementations of the fourth aspect, the method further includes: the second network node sending the AI ​​capability of the second network node to the control node or the first network node.

[0052] In combination with the fourth aspect, in certain implementations of the fourth aspect, before the second network node receives the processing result and target state information of the first task of the AI ​​task from the first network node, the method also includes: the second network node receives second request information from the first network node, and the second request information requests the second network node to collaborate in executing the AI ​​task.

[0053] In combination with the fourth aspect, in certain implementations of the fourth aspect, the processing result of the first task represents the current state information of the AI ​​task; the second network node executes the second task of the AI ​​task based on the processing result of the first task and the target state information, including: the second network node executes the second task of the AI ​​task based on the current state information and the target state information of the AI ​​task.

[0054] In combination with the fourth aspect, in certain implementations of the fourth aspect, the method further includes: the second network node receives area information from the first network node, and the area information is used by the second network node to determine the network node that collaborates to perform the AI ​​task.

[0055] In combination with the fourth aspect, in certain implementations of the fourth aspect, the method further includes: the second network node sending the second task or a portion of the second task to at least one terminal device.

[0056] In combination with the fourth aspect, in certain implementations of the fourth aspect, at least one terminal device is in a preset state.

[0057] In combination with the fourth aspect, in certain implementations of the fourth aspect, before the second network node sends the second task or part of the second task to at least one terminal device, the method also includes: the second network node sends notification information to at least one terminal device, and the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0058] The beneficial effects of the fourth aspect and each possible design can be referred to the relevant description of the third aspect and will not be repeated here.

[0059] In a fifth aspect, a method for AI task indication is provided, which can be executed by a network node. The network node can be a device, or a chip (system) or circuit for a device, which is not limited in this application.

[0060] The method may include: a network node sending an AI task to at least one terminal device, wherein the at least one terminal device is in a preset state.

[0061] Based on the above technical solution, by defining different states for terminals, it is possible to facilitate network nodes to determine whether a terminal is capable of executing an AI task based on the terminal's state. For example, a network node can send an AI task to a terminal in a preset state, that is, the AI ​​in the preset state can execute the AI ​​task.

[0062] In combination with the fifth aspect, in certain implementations of the fifth aspect, before the network node sends the AI ​​task to at least one terminal device, the method also includes: the network node sends notification information to the at least one terminal device, and the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0063] In a sixth aspect, a method for AI task indication is provided, which can be executed by a terminal device. The terminal device can be a device, or a chip (system) or circuit for a device, which is not limited in this application.

[0064] The method may include: a terminal device receiving an AI task from a network node, wherein the terminal device is in a preset state; and the terminal device executing the AI ​​task.

[0065] In combination with the sixth aspect, in certain implementations of the sixth aspect, before the terminal device receives the AI ​​task from the network node, the method also includes: the terminal device receives notification information from the network node, and the notification information notifies that the terminal device is adjusted to a preset state.

[0066] The beneficial effects of the sixth aspect and each possible design can be referred to the relevant description of the fifth aspect and will not be repeated here.

[0067] In a seventh aspect, a method for AI task indication is provided. The method can be performed by a communication system, and the communication information includes, for example, a control node and a network node. The control node and the network node can be devices, or chips (systems) or circuits for devices, which are not limited in this application.

[0068] The method may include: a control node determining first orchestration information for an AI task, the first orchestration information instructing a first network node to perform a first task of the AI ​​task; the control node sending the first orchestration information to the first network node; and the first network node performing the first task according to the first orchestration information.

[0069] The control node may be, for example, the control node described in the first aspect, and the first network node may be, for example, the first network node described in the second aspect.

[0070] The beneficial effects of the seventh aspect can be referred to the relevant description of the first aspect and will not be repeated here.

[0071] In an eighth aspect, a method for AI task indication is provided. The method can be performed by a communication system, and the communication information includes, for example, a first network node and a second network node. The first network node and the second network node can be devices, or chips (systems) or circuits for devices, which are not limited in this application.

[0072] The method may include: a first network node sending a processing result and target state information of a first task of an AI task to a second network node, where the target state information is used to indicate a target result of the AI ​​task; and the second network node executing a second task of the AI ​​task based on the processing result and target state information of the first task.

[0073] The first network node may be, for example, the first network node described in the third aspect, and the second network node may be, for example, the second network node described in the fourth aspect.

[0074] The beneficial effects of the eighth aspect can be referred to the relevant description of the third aspect and will not be repeated here.

[0075] In a ninth aspect, a method for AI task indication is provided. The method can be executed by a communication system, and the communication information includes, for example, network nodes and terminal devices. The network nodes and terminal devices can be devices, or chips (systems) or circuits for devices, which are not limited in this application.

[0076] The method may include: a network node sending an AI task to at least one terminal device, wherein the at least one terminal device is in a preset state; and the at least one terminal device executing the AI ​​task.

[0077] The network node may be, for example, the network node described in the fifth aspect, and the terminal device may be, for example, the terminal device described in the sixth aspect.

[0078] The beneficial effects of the ninth aspect can be referred to the relevant description of the fifth aspect and will not be repeated here.

[0079] In a tenth aspect, a communication device is provided, the device being configured to execute the method provided in any one of aspects 1 to 9. Specifically, the device may include units and / or modules, such as a processing unit and / or a communication unit, for executing the method provided in any one of the above implementations of aspects 1 to 9.

[0080] In one implementation, the apparatus is a communication device. When the apparatus is a communication device, the communication unit may be a transceiver or an input / output interface; the processing unit may be at least one processor. Alternatively, the transceiver may be a transceiver circuit. Alternatively, the input / output interface may be an input / output circuit.

[0081] In another implementation, the apparatus is a chip, chip system, or circuit used in a communication device. When the apparatus is a chip, chip system, or circuit used in a terminal device, the communication unit may be an input / output interface, interface circuit, output circuit, input circuit, pin, or related circuit on the chip, chip system, or circuit; and the processing unit may be at least one processor, processing circuit, or logic circuit.

[0082] In the eleventh aspect, a communication device is provided, which includes: a memory for storing programs; and at least one processor for executing computer programs or instructions stored in the memory to execute the method provided in any one of the above-mentioned implementations of any one of the above-mentioned aspects from the first to the ninth aspect.

[0083] In one implementation, the apparatus is a communication device.

[0084] In another implementation, the apparatus is a chip, a chip system, or a circuit used in a communication device.

[0085] In a twelfth aspect, the present application provides a processor for executing the methods provided in the above aspects.

[0086] For the operations such as sending and acquiring / receiving involved in the processor, unless otherwise specified, or if they do not conflict with their actual functions or internal logic in the relevant descriptions, they can be understood as operations such as processor output and input, or as sending and receiving operations performed by the radio frequency circuit and antenna. This application does not limit this.

[0087] In the thirteenth aspect, a computer-readable storage medium is provided, which stores a program code for execution by a device, and the program code includes a method provided by any one of the above-mentioned implementation methods for executing any one of the above-mentioned aspects from the first to the ninth aspect.

[0088] In the fourteenth aspect, a computer program product comprising instructions is provided, which, when run on a computer, enables the computer to execute the method provided by any one of the above-mentioned implementations of any one of the above-mentioned aspects from the first to the ninth aspect.

[0089] In the fifteenth aspect, a chip is provided, which includes a processor and a communication interface. The processor reads instructions stored in a memory through the communication interface and executes the method provided by any of the above-mentioned implementation methods of any of the above-mentioned aspects from the first to the ninth aspect.

[0090] Optionally, as an implementation method, the chip also includes a memory, in which a computer program or instruction is stored, and the processor is used to execute the computer program or instruction stored on the memory. When the computer program or instruction is executed, the processor is used to execute the method provided in any one of the above-mentioned implementation methods of any one of the first to ninth aspects.

[0091] In a sixteenth aspect, a communication system is provided, comprising the control node in the first aspect and the first network node in the second aspect.

[0092] Optionally, the communication system further includes a second network node.

[0093] In a seventeenth aspect, a communication system is provided, comprising the first network node in the third aspect and the second network node in the fourth aspect.

[0094] In an eighteenth aspect, a communication system is provided, comprising the network node in the fifth aspect and the terminal device in the sixth aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] FIG1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of the present application.

[0096] FIG2 is a schematic diagram of a wireless communication system according to an embodiment of the present application.

[0097] FIG3 is a schematic diagram of a method 300 for AI task indication according to an embodiment of the present application.

[0098] FIG4 is a schematic diagram of a method 400 for AI task indication provided by another embodiment of the present application.

[0099] FIG5 is a schematic diagram of a method 500 for AI task indication provided by another embodiment of the present application.

[0100] FIG6 is a schematic flowchart of a method 600 for AI task indication according to an embodiment of the present application.

[0101] FIG. 7 is a schematic diagram applicable to an embodiment of the present application.

[0102] FIG8 is a schematic flowchart of a method 800 for AI task indication according to another embodiment of the present application.

[0103] FIG9 is a schematic flowchart of a method 900 for AI task indication according to another embodiment of the present application.

[0104] FIG10 is a schematic block diagram of a communication device 1000 provided in an embodiment of the present application.

[0105] FIG11 is a schematic block diagram of a communication device 1100 provided in an embodiment of the present application.

[0106] FIG12 is a schematic block diagram of a chip system 1200 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0107] The technical solution of this application will be described below with reference to the accompanying drawings.

[0108] First, a brief introduction to the relevant concepts and technologies involved in this application is given.

[0109] 1. Artificial intelligence (AI) model: It is an algorithm or computer program that can realize AI functions. The AI ​​model represents the mapping relationship between the input and output of the model, or in other words, the AI ​​model is a function model that maps input of a certain dimension to output of a certain dimension. The parameters of the function model can be obtained through machine learning training. For example, f(x) = ax 2 +b is a quadratic function model, which can be regarded as an AI model. a and b are the parameters of the AI ​​model, and a and b can be obtained through machine learning training.

[0110] It is understood that the AI ​​model can be implemented as a hardware circuit, software, or a combination of software and hardware, without limitation. Non-limiting examples of software include: program code, program, subroutine, instruction, instruction set, code, code segment, software module, application, or software application.

[0111] 2. Dataset: Data used for model training, model validation, or model testing in machine learning. The quantity and quality of the data will affect the effectiveness of machine learning.

[0112] 3. Model training: By selecting an appropriate loss function and using an optimization algorithm to train the model parameters, the loss function is minimized. The loss function is used to measure the difference between the model's predicted value and the true value.

[0113] 4. AI tasks: These tasks are related to AI. For example, AI tasks may include tasks related to models (such as AI models) and tasks related to datasets.

[0114] The following briefly introduces the communication system applicable to this application.

[0115] The technical solutions provided in this application can be applied to various communication systems, such as: fifth generation (5G) or new radio (NR) systems, long term evolution (LTE) systems, LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, etc. The technical solutions provided in this application can also be applied to future communication systems, such as the sixth generation mobile communication system. The technical solutions provided in this 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 Internet of Things (IoT) communication systems or other communication systems.

[0116] The terminal devices in the embodiments of the present application include various devices with wireless communication functions, which can be used to connect people, objects, machines, etc. The terminal devices can be widely used in various scenarios, such as: cellular communication, D2D, V2X, peer to peer (P2P), M2M, MTC, IoT, virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery, etc. The terminal device can be a terminal in any of the above scenarios, such as an MTC terminal, an IoT terminal, etc. The terminal device may be a user equipment (UE) of the third generation partnership project (3GPP) standard, a terminal, a fixed device, a mobile station device or a mobile device, a subscriber unit, a handheld device, a vehicle-mounted device, a wearable device, a cellular phone, a smart phone, a SIP phone, a wireless data card, a personal digital assistant (PDA), a computer, a tablet computer, a notebook computer, a wireless modem, a handheld device, a laptop computer, a computer with wireless transceiver function, a smart book, a vehicle, a satellite, a global positioning system (GPS) device, a target tracking device, an aircraft (such as a drone, a helicopter, a multi-copter, a quadcopter, or an airplane), a ship, a remote control device, a smart home device, an industrial device, or a device built into the above-mentioned device (such as a communication module, a modem or a chip in the above-mentioned device), or other processing devices connected to a wireless modem. For ease of description, the terminal device will be described below by taking the terminal or UE as an example.

[0117] It should be understood that in some scenarios, a UE can also be used to act as a base station. For example, a UE can act as a scheduling entity that provides sidelink signals between UEs in scenarios such as V2X, D2D, or P2P.

[0118] In the embodiments of the present application, the device for implementing the function of the terminal device can be the terminal device, or it can be a device that can support the terminal device to implement the function, such as a chip system or chip, which can be installed in the terminal device. In the embodiments of the present application, the chip system can be composed of a chip, or it can include a chip and other discrete devices.

[0119] The network device in the embodiments of the present application may be a device for communicating with a terminal device, and may also be referred to as an access network device or a radio access network device. For example, the network device may be a base station. The network device in the embodiments of the present application may refer to a radio access network (RAN) node (or device) that connects a terminal device to a wireless network. Base station can broadly cover various names as follows, or replace the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), relay station, access point, transmission point (TRP), transmission point (TP), master station, auxiliary station, multi-standard wireless (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), positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The base station can also refer to a communication module, modem or chip used to be set in the aforementioned device or apparatus. The base station can also be a mobile switching center and a device that performs base station functions in D2D, V2X, and M2M communications, a network-side device in a 6G network, or a device that performs base station functions in future communication systems. The base station can support networks with the same or different access technologies. The embodiments of this application do not limit the specific technology and specific device form used by the network equipment.

[0120] Base stations can be fixed or mobile. For example, a helicopter or drone can be configured to act as a mobile base station, and at least one cell can move based on the location of the mobile base station. In other examples, a helicopter or drone can be configured to act as a device that communicates with another base station.

[0121] The network equipment and terminal devices can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which the network equipment and terminal devices are located.

[0122] Referring to Figure 1 , as an example, Figure 1 is a schematic diagram of a wireless communication system 100 applicable to an embodiment of the present application. As shown in Figure 1 , the wireless communication system 100 may include at least one network device, such as the network device 110 shown in Figure 1 . The wireless communication system 100 may also include at least one terminal device, such as the terminal device 120 and the terminal device 130 shown in Figure 1 . Both the network device and the terminal device may be configured with multiple antennas, and the network device and the terminal device may communicate using multi-antenna technology. Terminal devices may also communicate directly with each other.

[0123] When a network device and a terminal device communicate, the network device can manage at least one cell, and a cell can have at least one terminal device. Optionally, network device 110 and terminal device 120 form a single-cell communication system. Without loss of generality, the cell is referred to as cell #1. Network device 110 can be a network device in cell #1, or network device 110 can serve a terminal device (e.g., terminal device 120) in cell #1.

[0124] It should be noted that a cell can be understood as an area within the coverage range of wireless signals of network equipment.

[0125] It is understood that Figure 1 is a simplified schematic diagram for ease of understanding, and the wireless communication system 100 may also include other network devices or other terminal devices, which are not shown in Figure 1. The embodiments of the present application can be applied to any communication scenario in which a transmitting device and a receiving device communicate.

[0126] To meet the vision of intelligent and inclusive future, intelligence will further evolve at the wireless network architecture level. AI will be further integrated with wireless networks, enabling endogenous network and terminal intelligence, thereby addressing a range of potential new demands and scenarios. For example, one possible scenario involves diversified terminal types, with more flexible and intelligent terminal connections. This includes the super IoT (such as the Internet of Things, connected vehicles, industrial, and medical), massive connections, more flexible terminal connections, and terminals with inherent AI capabilities. Another possible requirement is endogenous network intelligence. In addition to traditional communication and connectivity services, networks may also offer computing and AI services to better support inclusive, real-time, and highly secure AI services. These new demands and scenarios may lead to changes in wireless network architecture and communication models.

[0127] Currently, 3GPP has introduced AI capabilities in 5G networks by adding a new network data analytics function (NWDAF). The main functions of NWDAF include: supporting data collection from other network functions (NF) and application functions (AF), supporting data collection from network operation and maintenance systems (such as operation administration and maintenance (OAM)), and providing metadata exposure services and data analysis services to NF or AF. The main goals of introducing NWDAF include: automation and intelligence of network operation and maintenance, optimization of network performance and service experience, and end-to-end service level agreement (SLA) guarantees. The AI ​​model trained by NWDAF can be applied to network-specific areas such as mobility management, session management, and network automation, using AI methods to replace the numerical formula-based methods in the original network functions. However, NWDAF is deployed in the core network and is an external AI unit. It is not designed to be strongly coupled with the communication network, and its performance is limited.

[0128] Based on the potential scenarios and demands facing future wireless networks, the number and types of intelligent terminals in communication networks are expected to grow rapidly. The massive amounts of data collected, processed, and generated by these intelligent terminals will fuel the application of AI technologies. In this context, a large number of AI nodes will likely be deployed in wireless networks, generating a correspondingly large amount of AI-related traffic between these nodes, including data sets, AI models, and intermediate parameters. Therefore, a transmission mechanism for AI-related traffic can be designed to more closely integrate the network with AI and provide better AI services.

[0129] Based on this, the present application proposes to maintain the AI ​​capabilities of each network node in the wireless network. In this way, each network node can be orchestrated based on the AI ​​capabilities of each network node, that is, to determine how each network node collaborates to process AI tasks; or, the network node can obtain the AI ​​capability information of other network nodes according to demand, so that multiple network nodes can collaborate to process AI tasks.

[0130] Referring to Figure 2, as an example, Figure 2 is a schematic diagram of a wireless communication system according to an embodiment of the present application. As shown in Figure 2, the wireless communication system may include a network node, such as a RAN. The wireless communication system may also include an AI node, such as an AI management function (AI management function, AI-MF) and an AI function (AI-F). The network node and the AI ​​node can communicate directly or indirectly (such as through forwarding by other nodes).

[0131] Optionally, the AI ​​node may store or maintain the AI ​​capabilities of the network node. The AI ​​capabilities of the network node may also be referred to as AI-related parameters of the network node, and will be referred to as the AI ​​capabilities of the network node below.

[0132] Among them, the AI ​​capability of the network node may include, for example, at least one of the following: the priority of the network node, the computing power supported by the network node (such as the maximum computing power supported by the network node), the hardware capability of the network node, the AI ​​tasks supported by the network node, the performance of the local AI model of the network node, and the performance of the local data set of the network node. As an example, the priority of the network node can be determined based on the historical response of the network node. For example, if the network node participates in the collaborative processing of AI tasks more times, the priority of the network node is higher; if the network node participates in the collaborative processing of AI tasks less times, the priority of the network node is lower. As another example, the priority of the network node can be determined based on the capabilities of the network node (such as the supported computing power, and the hardware capabilities of the network node itself, etc.). For example, if the capabilities of the network node are higher, the priority of the network node is higher; if the capabilities of the network node are lower, the priority of the network node is lower.

[0133] It will be understood that the above is an exemplary description and is not intended to be limiting. For example, the AI ​​capabilities of a network node may also include security requirements of the network node.

[0134] Optionally, the AI ​​node can be deployed in the core network; or the AI ​​node can be deployed outside the core network, such as in a network node; or the AI ​​node can be deployed in an operation and maintenance management system independently configured by the operator. As an example, as shown in Figure 2, the AI ​​node AI-MF can be deployed in the core network, and the RAN and AI-MF can communicate via the NG interface. As another example, as shown in Figure 2, the AI ​​node AI-F can be deployed in the RAN, and other modules in the RAN can communicate with the AI-F via an internal interface.

[0135] It can be understood that an AI node can be an independent device, or it can be integrated into the same device to implement certain functions, or it can be a network element in a hardware device, or it can be a software function running on dedicated hardware, or it can be a virtualized function instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0136] It is also understood that FIG2 is an exemplary illustration and the present application is not limited thereto. For example, the communication system shown in FIG2 may also include a larger number of devices, such as a larger number of terminals, a larger number of AI nodes, a larger number of network nodes, and so on.

[0137] The above briefly introduces the communication system provided according to the embodiment of the present application in conjunction with Figure 2. The following describes the method provided by the embodiment of the present application. The method described below can be used in the system shown in Figure 2.

[0138] It should be noted that in this application, "indication" can include direct indication, indirect indication, explicit indication, and implicit indication. When describing that a certain indication information is used to indicate A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A.

[0139] In this application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved with the help of the arrangement order of each information agreed in advance (such as specified in the protocol), thereby reducing the indication overhead to a certain extent.

[0140] The information to be indicated can be sent as a whole, or divided into multiple sub-information and sent separately, and the sending period and / or sending timing of these sub-information can be the same or different. The specific sending method is not limited in this application. The sending period and / or sending timing of these sub-information can be predefined, for example, predefined according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device. The configuration information can include, for example, but not limited to, one or a combination of at least two of radio resource control signaling, media access control (MAC) layer signaling, and physical layer signaling. The radio resource control signaling includes, for example, radio resource control (RRC) signaling; the MAC layer signaling includes, for example, a MAC control element (CE); and the physical layer signaling includes, for example, downlink control information (DCI).

[0141] 3 , as an example, is a schematic diagram of a method 300 for AI task indication provided by an embodiment of the present application. The method 300 may include the following steps.

[0142] 310. The control node determines first orchestration information for the AI ​​task, where the first orchestration information instructs a first network node to execute a first task of the AI ​​task.

[0143] Among them, the AI ​​task can be determined by the control node itself, or it can be requested by other nodes (such as network nodes, terminals, core network nodes, AI nodes, etc.), without restriction.

[0144] The control node may be, for example, an AI node, such as the AI-MF or AI-F shown in FIG2 . The network node may be, for example, a network device, such as the RAN shown in FIG2 .

[0145] The first network node may be the first network node participating in executing the AI ​​task, or the first network node may be any network node participating in executing the AI ​​task.

[0146] For example, assume that two network nodes participate in executing an AI task, namely, a first network node and a second network node. If the first network node executes the AI ​​task first, such as executing a portion of the AI ​​task (e.g., the first task), and after the first network node completes the first task, the second network node continues to execute the AI ​​task, such as executing the remaining portion of the AI ​​task (e.g., the second task), then the first network node can be considered the first network node to participate in executing the AI ​​task, and the second network node can be considered the next network node (or next-hop network node) of the first network node.

[0147] The first orchestration information instructs the first network node to perform the first task of the AI ​​task, and the first orchestration information may directly instruct the first network node to perform the first task of the AI ​​task, such as the first orchestration information includes the first task; or the first orchestration information may indirectly instruct the first network node to perform the first task of the AI ​​task, such as the first orchestration information includes the other information, and the other information may indirectly indicate the first task.

[0148] Optionally, the first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for executing the first task, and an exit condition for the first network node to execute the first task.

[0149] 1) The first task refers to the portion of the AI ​​task (or decomposed task) that the first network node is responsible for when the first network node participates in executing the AI ​​task, or the operation provided by the first network node when the first network node participates in executing the AI ​​task.

[0150] If the first orchestration information includes the first task, the first orchestration information can directly instruct the first network node to perform the first task of the AI ​​task, that is, the first network node can directly obtain the operations that need to be provided when performing the AI ​​task based on the first orchestration information, and then perform the first task based on the first orchestration information.

[0151] 2) An identifier of the first network node, used to identify that the network nodes participating in executing the AI ​​task include the first network node.

[0152] If the first orchestration information includes the identifier of the first network node, the first orchestration information may indirectly instruct the first network node to execute the first task of the AI ​​task. Specifically, the first network node may learn that it is participating in the execution of the AI ​​task based on the identifier of the first network node in the first orchestration information. In this case, the first network node may participate in the execution of the AI ​​task based on its own AI capabilities. In this way, the first network node may determine the operations required to perform the AI ​​task based on its own AI capabilities, that is, determine the first task.

[0153] 3) Resources provided by the first network node to perform the first task, indicating the resources that the first network node needs to provide when participating in the execution of the AI ​​task, such as the required computing power and the required hardware capabilities.

[0154] If the first orchestration information includes resources provided by the first network node for executing the first task, the first orchestration information may indirectly instruct the first network node to execute the first task of the AI ​​task. Specifically, the first network node may execute the AI ​​task based on the resources provided by the first network node for executing the first task in the first orchestration information. In this way, the first network node can determine when to stop executing the AI ​​task based on the resources and, further, determine the operations required to be performed while executing the AI ​​task, i.e., determine the first task.

[0155] 4) The exit condition for the first network node to execute the first task indicates the condition for the first network node to transfer the AI ​​task to the next network node for continued processing, or the condition for the first network node to stop executing the AI ​​task, which can be used by the first network node to determine when to stop executing the AI ​​task.

[0156] If the first orchestration information includes an exit condition for the first network node to execute the first task, the first orchestration information may indirectly instruct the first network node to execute the first task of the AI ​​task. Specifically, the first network node may execute the AI ​​task based on the exit condition for the first network node to execute the first task. In this way, the first network node can determine when to cease executing the AI ​​task based on the exit condition and, further, determine the operations to be performed while executing the AI ​​task, i.e., determine the first task.

[0157] It can be understood that for the last network element node, its exit condition for executing the AI ​​task, that is, the condition for stopping executing the AI ​​task, the last network node does not need to transfer the AI ​​task to other network nodes (such as the next network node). For example, if the first network node is the last network node, that is, the first network element node executes the first task based on the exit condition of the first network node, after executing the first task, what is obtained is the final result of the AI ​​task. In this case, as an example, the first network element node can directly send the final result of the AI ​​task to the initiating node of the AI ​​task (such as a terminal device), or the first network element node can send the final result of the AI ​​task to other nodes, and the other nodes send the final result of the AI ​​task to the initiating node of the AI ​​task.

[0158] 320. The control node sends first orchestration information to the first network node.

[0159] Optionally, the method 300 further includes: the first network node executing a first task of the AI ​​task based on the first orchestration information.

[0160] Based on the embodiments of the present application, a control node can determine the orchestration information for an AI task and send the orchestration information to the network node, which can then execute the AI ​​task based on the orchestration information. In this way, the control node can determine the appropriate orchestration information based on the AI ​​task, improving overall efficiency.

[0161] Optionally, the control node determines first orchestration information for the AI ​​task, including: the control node determining an orchestration table for the AI ​​task, the orchestration table including orchestration information of N network nodes, where the N network nodes include the first network node, and N is an integer greater than or equal to 1. In this way, unified orchestration can be performed by the control node, improving overall efficiency. The orchestration table includes the orchestration information of the N network nodes, that is, the orchestration information of the N network nodes can be considered as one orchestration table.

[0162] For example, assume that N network nodes include a first network node and a second network node. The control node determines first orchestration information and second orchestration information for an AI task. The second orchestration information instructs the second network node to execute the second task of the AI ​​task. For the orchestration information of each network node, refer to the description of the orchestration information of the first network node (i.e., the first orchestration information) above and will not be repeated here.

[0163] As an example, the arrangement table may exist in the form of a table, a function, or a string, such as for storage or transmission. Table 1 below is an example of an arrangement table presented in a table form.

[0164] Table 1

[0165] Network node Orchestration information of network node First network node First orchestration information Second network node Second orchestration information

[0166] Taking Table 1 as an example, the orchestration information of the first network node is the first orchestration information, that is, the first orchestration information instructs the first network node to perform the first task of the AI ​​task; the orchestration information of the second network node is the second orchestration information, that is, the second orchestration information instructs the second network node to perform the second task of the AI ​​task.

[0167] It is understood that Table 1 is merely an example and is not limiting, and any variation of Table 1 is applicable to the present application. For example, Table 1 may also include a greater number of network nodes.

[0168] As an example, the scheduling information of each network node may be transmitted in any of the following ways.

[0169] In a first possible implementation manner, the control node sends an orchestration table to each of the N network nodes.

[0170] Based on this implementation, each of the N network nodes can obtain the orchestration table from the control node, and further obtain its own orchestration information according to the orchestration table.

[0171] For example, assume that the N network nodes include a first network node and a second network node, and the orchestration table includes orchestration information of the first network node and orchestration information of the second network node. The orchestration information of the first network node is first orchestration information, and the orchestration information of the second network node is second orchestration information. Based on this implementation, the control node sends the first orchestration information and the second orchestration information to the first network node, and the control node sends the first orchestration information and the second orchestration information to the second network node.

[0172] In a second possible implementation manner, the control node sends the orchestration table to one network node (eg, the first network node) among the N network nodes.

[0173] The first network node may be the first network node participating in executing the AI ​​task, or the first network node may be any network node participating in executing the AI ​​task.

[0174] In Example 1, a first network node sends an orchestration table to other network nodes in N network nodes. For example, after receiving the orchestration table, the first network node may directly send the orchestration table to other network nodes in the N network nodes. In another example, after the first network node completes executing its own AI task based on the orchestration table, it sends the orchestration table to other network nodes in the N network nodes.

[0175] For example, assume that the N network nodes include a first network node and a second network node, and the orchestration table includes orchestration information of the first network node and orchestration information of the second network node. The orchestration information of the first network node is first orchestration information, and the orchestration information of the second network node is second orchestration information. Based on Example 1, the control node sends the first orchestration information and the second orchestration information to the first network node, and the first network node sends the first orchestration information and the second orchestration information to the second network node.

[0176] Example 2: The first network node sends the orchestration information of the other network nodes to the other network nodes in the N network nodes. For example, after receiving the orchestration table, the first network node can directly send the orchestration information of the other network nodes in the orchestration table to the other network nodes in the N network nodes. For another example, after the first network node completes the AI ​​task for which it is responsible based on the orchestration table, it sends the orchestration information of the other network nodes in the orchestration table to the other network nodes in the N network nodes.

[0177] For example, assume that the N network nodes include a first network node and a second network node, and the orchestration table includes orchestration information for the first network node and orchestration information for the second network node. The orchestration information for the first network node is first orchestration information, and the orchestration information for the second network node is second orchestration information. Based on Example 2, the control node sends the first orchestration information and the second orchestration information to the first network node, and the first network node sends the second orchestration information to the second network node.

[0178] In Example 3, a first network node sends an orchestration table to the next network node of the first network node, and the next network node sends an orchestration table to the next network node of the next network node, and so on. For example, after receiving the orchestration table, the first network node can directly send the orchestration table to the next network node of the first network node. For another example, after the first network node completes the AI ​​task for which it is responsible based on the orchestration table, it sends the orchestration table to the next network node of the first network node.

[0179] For example, assuming that N network nodes include a first network node, a second network node, and a third network node, and the orchestration table includes orchestration information for the first network node, the second network node, and the third network node, the orchestration information for the first network node is first orchestration information, the orchestration information for the second network node is second orchestration information, and the orchestration information for the third network node is third orchestration information. Based on Example 3, the control node sends the first orchestration information, the second orchestration information, and the third orchestration information to the first network node, the first network node sends the first orchestration information, the second orchestration information, and the third orchestration information to the second network node, and the second network node sends the first orchestration information, the second orchestration information, and the third orchestration information to the third network node.

[0180] Example 4: The first network node sends the orchestration information in the orchestration table other than the orchestration information of the first network node to the next network node of the first network node, and the next network node sends the orchestration information in the orchestration table received from the first network node other than the orchestration information of the current network node to the next network node of the next network node, and so on. For example, after receiving the orchestration table, the first network node can directly send the orchestration information in the orchestration table other than the orchestration information of the first network node to the next network node of the first network node. For another example, after the first network node completes the AI ​​task for which it is responsible based on the orchestration table, it sends the orchestration information in the orchestration table other than the orchestration information of the first network node to the next network node of the first network node.

[0181] For example, assume that N network nodes include a first network node, a second network node, and a third network node, and the orchestration table includes orchestration information for the first network node, the second network node, and the third network node. The orchestration information for the first network node is first orchestration information, the orchestration information for the second network node is second orchestration information, and the orchestration information for the third network node is third orchestration information. Based on Example 4, the control node sends the first orchestration information, the second orchestration information, and the third orchestration information to the first network node, the first network node sends the second and third orchestration information to the second network node, and the second network node sends the third orchestration information to the third network node.

[0182] In a third possible implementation manner, the control node sends the orchestration information of each network node to each network node among the N network nodes.

[0183] For example, assume that the N network nodes include a first network node and a second network node, and the orchestration table includes orchestration information for the first network node and orchestration information for the second network node. The orchestration information for the first network node is first orchestration information, and the orchestration information for the second network node is second orchestration information. Based on this implementation, the control node sends the first orchestration information to the first network node, and the control node sends the second orchestration information to the second network node.

[0184] It is understood that the above-mentioned possible implementations are exemplary and not limiting. For example, the control node may send an orchestration table to some of the N network nodes, which then send the orchestration table or orchestration information of each network node to other network nodes.

[0185] It is also understood that in any of the above possible implementations, when the first network node sends the second network node's orchestration information to the second network node, the first network node may also send the processing result of the first task to the second network node. In this way, the second network node can continue to execute the AI ​​task based on the processing result of the first task.

[0186] Optionally, the control node determines an orchestration table for the AI ​​task based on the AI ​​capabilities of the N network nodes. For example, the control node determines first orchestration information for the AI ​​task based on the AI ​​capabilities of the first network node. In this way, the orchestration information determined by the control node can match the AI ​​capabilities of each network node, reducing the probability that a network node will be unable to execute the AI ​​task.

[0187] As previously mentioned, the AI ​​capabilities of a network node may include, for example, at least one of the following: the network node's priority, the computing power supported by the network node, the network node's hardware capabilities, the AI ​​tasks supported by the network node, the performance of the network node's local AI model, and the performance of the network node's local dataset. The following examples illustrate how a control node determines an orchestration table for an AI task based on the AI ​​capabilities of N network nodes, in conjunction with the network node's AI capabilities.

[0188] Example 1: The control node determines an orchestration table for the AI ​​task according to the AI ​​tasks supported by the network node. That is, the control node determines orchestration information of the network node for the AI ​​task according to the AI ​​tasks supported by the network node.

[0189] For example, if the AI ​​task is a model training task, the control node can determine which network nodes support the model training task based on the AI ​​tasks supported by each network node. The control node can also determine the N network nodes that participate in executing the AI ​​task from among the network nodes that support the model training task. Furthermore, the operations that each of the N network nodes is responsible for and the resources they provide can be determined by the control node based on the network nodes' other AI capabilities, or by each network node independently based on its own AI capabilities during the execution of the AI ​​task, without limitation.

[0190] Example 2: The control node determines the orchestration table for the AI ​​task based on the computing power supported by the network node, that is, the control node determines the orchestration information of the network node for the AI ​​task based on the computing power supported by the network node.

[0191] For example, the control node determines that N network nodes with higher computing power will perform the AI ​​task based on the computing power supported by each network node. In addition, the control node can also determine the operations that each network node is responsible for and / or the resources provided by each network node based on the computing power supported by the N network nodes. It can be understood that the operations that each of the N network nodes is responsible for and the resources provided, etc., can also be determined by the control node based on other AI capabilities of the network nodes, or can also be determined by each network node based on its own AI capabilities during the execution of the AI ​​task, without limitation.

[0192] Example 3: The control node determines an orchestration table for the AI ​​task based on the hardware capabilities of the network nodes. That is, the control node determines the orchestration information of the network nodes for the AI ​​task based on the hardware capabilities of the network nodes.

[0193] For example, the control node determines, based on the hardware capabilities of each network node, that N network nodes with higher hardware capabilities will perform the AI ​​task. Furthermore, the control node may also determine, based on the hardware capabilities of the N network nodes, the operations for which each network node is responsible and / or the resources provided by each network node. It is understood that the operations for which each of the N network nodes is responsible and the resources provided, etc., may also be determined by the control node based on other AI capabilities of the network nodes, or may be determined independently by each network node based on its own AI capabilities during the execution of the AI ​​task, without limitation.

[0194] Example 4: The control node determines a scheduling table for the AI ​​task based on the performance of the local AI model of the network node, that is, the control node determines the scheduling information of the network node for the AI ​​task based on the performance of the local AI model of the network node.

[0195] For example, the performance of a local AI model on a network node may include, but is not limited to, accuracy and timeliness. Accuracy may represent the performance of the AI ​​model in executing certain tasks, while timeliness may represent the time it takes to generate the AI ​​model.

[0196] For example, the control node determines that N network nodes with higher performance will perform the AI ​​task based on the performance of the local AI model of the network node. In addition, the control node can also determine the operations for which each network node is responsible and / or the resources provided by each network node based on the performance of the local AI model of the N network nodes. It can be understood that the operations for which each of the N network nodes is responsible and the resources provided, etc., can also be determined by the control node based on other AI capabilities of the network nodes, or can also be determined by each network node based on its own AI capabilities during the execution of the AI ​​task, without limitation.

[0197] Example 5: The control node determines an orchestration table for the AI ​​task based on the performance of the local data set of the network node. That is, the control node determines the orchestration information of the network node for the AI ​​task based on the performance of the local data set of the network node.

[0198] As an example, the performance of a local dataset of a network node may include, but is not limited to, accuracy and timeliness. Accuracy may represent the performance of the dataset under several test models, while timeliness may represent the time when the dataset was generated.

[0199] For example, the control node determines that N network nodes with higher performance will perform the AI ​​task based on the performance of the local data sets of the network nodes. In addition, the control node can also determine the operations responsible for each network node and / or the resources provided by each network node based on the performance of the local data sets of the N network nodes. It is understood that the operations responsible for and the resources provided by the N network nodes can also be determined by the control node based on other AI capabilities of the network nodes, or can be determined by each network node based on its own AI capabilities during the execution of the AI ​​task, without limitation.

[0200] Example 6: The control node determines the orchestration table according to the priority of the network node, that is, the control node determines the orchestration information of the network node for the AI ​​task according to the priority of the network node.

[0201] For example, based on the priorities of the network nodes, the control node determines that N network nodes with higher priorities will perform the AI ​​task. Furthermore, the operations and resources provided by each of the N network nodes can be determined by the control node based on other AI capabilities of the network nodes, or by each network node independently during the execution of the AI ​​task based on its own AI capabilities, without limitation.

[0202] Example 7: The control node determines an orchestration table for the AI ​​task based on the AI ​​tasks supported by the network node and the computing power supported by N network nodes. That is, the control node determines the orchestration information of the network node for the AI ​​task based on the AI ​​tasks supported by the network node and the computing power supported by N network nodes.

[0203] For example, if the AI ​​task requested by the communication node is a model training task, the control node can determine which network nodes support the model training task based on the AI ​​tasks supported by each network node. The control node can also determine the N network nodes that will participate in executing the AI ​​task from among the network nodes that support the model training task. Furthermore, the control node can determine the operations that each network node is responsible for and the resources it provides based on the computing power supported by the N network nodes.

[0204] It is understood that the above examples are illustrative and not limiting. For example, the control node may determine an orchestration table for an AI task based on at least one of the following: the priority of the network node, the computing power supported by the network node, the hardware capabilities of the network node, the AI ​​tasks supported by the network node, the performance of the network node's local AI model, and the performance of the network node's local dataset.

[0205] Optionally, the control node may obtain the AI ​​capabilities of the N network nodes in any of the following ways.

[0206] In a first possible implementation, a control node locally maintains the AI ​​capabilities of at least one network node, and the control node can directly determine an orchestration table for the AI ​​task based on the locally maintained AI capabilities of the at least one network node. The at least one network node includes N network nodes.

[0207] As an example, the AI ​​capability of at least one network node may be present in the form of a table, a function, or a string, such as for storage or transmission. Table 2 below is an example of presenting the AI ​​capability of at least one network node in table form.

[0208] Table 2

[0209] AI capability of network node network node first network node AI capability of first network node second network node AI capability of second network node third network node AI capability of third network node

[0210] It is understood that Table 2 is merely an example and is not intended to limit the present invention. Any variation of Table 2 is applicable to the present invention. For example, Table 2 may include a greater number of network nodes.

[0211] In a second possible implementation, after confirming the AI ​​task, the control node requests the AI ​​capabilities of at least one network node from other nodes, and then determines an orchestration table for the AI ​​task based on the AI ​​capabilities of the at least one network node. The at least one network node includes N network nodes.

[0212] In a third possible implementation, after confirming the AI ​​task, the control node requests the AI ​​capabilities of at least one network node, and then determines an orchestration table for the AI ​​task based on the AI ​​capabilities of the at least one network node. The at least one network node includes N network nodes.

[0213] Optionally, the AI ​​capability of the network node can be updated. Taking the control node maintaining the AI ​​capability of the network node as an example, two examples are described below.

[0214] In one example, the control node periodically updates the AI ​​capabilities of the network node. For example, the network node periodically reports its AI capabilities to the control node, and the control node can periodically update the AI ​​capabilities of the network node. In another example, the control node periodically sends information to the network node, and the information is used to trigger the network node to report its AI capabilities to the control node, and the control node can periodically update the AI ​​capabilities of the network node.

[0215] In another example, after an event is triggered, the control node updates the AI ​​capabilities of the network node. For example, a network node reports its AI capabilities to the control node. If the reported AI capabilities are inconsistent with the previously stored AI capabilities of the network node, the control node updates the AI ​​capabilities of the network node. In another example, after determining the orchestration information for an AI task, the network node updates the AI ​​capabilities of the network node.

[0216] Optionally, the method 300 further includes: the control node receiving response information from the first network node, where the response information indicates whether the first network node agrees with the first orchestration information.

[0217] In one possible scenario, the first network node agrees with the first orchestration information, so the response information sent by the first network node to the control node indicates that the first network node agrees with the first orchestration information.

[0218] In another possible scenario, the first network node disagrees with the first orchestration information, so the response information sent by the first network node to the control node indicates that the first network node disagrees with the first orchestration information.

[0219] Whether the first network node agrees (or accepts) the first orchestration information can be understood as whether the first network node agrees to execute the first task.

[0220] The response information indicates whether the first network node agrees with the first orchestration information, including any one of the following implementations.

[0221] In a first possible implementation manner, the response information directly indicates whether the first network node agrees with the first orchestration information.

[0222] For example, the response information may be implemented as a positive acknowledgement or a negative acknowledgement. For example, if the first network node agrees with the first orchestration information, the first network node sends a positive acknowledgement to the control node; if the first network node disagrees with the first orchestration information, the first network node sends a negative acknowledgement to the control node.

[0223] As another example, the response information may be implemented using at least one bit. For example, assume that a single bit indicates whether the first network node agrees with the first orchestration information. If this bit is set to "1," it indicates that the first network node agrees with the first orchestration information; if this bit is set to "0," it indicates that the first network node disagrees with the first orchestration information. It should be understood that the above description is merely illustrative and not limiting.

[0224] In a second possible implementation manner, the response information indirectly indicates whether the first network node agrees with the first orchestration information.

[0225] For example, the first network node sends adjusted first orchestration information to the control node. The adjusted first orchestration information may indirectly indicate that the first network node disagrees with the first orchestration information. That is, the control node learns that the first network node disagrees with the first orchestration information based on the adjusted first orchestration information. The adjusted first orchestration information may include, but is not limited to, an adjusted first task and / or resources that the first network node can provide to perform the first task.

[0226] It will be understood that the above two implementations are exemplary and not limiting. For example, if the control node does not receive a negative response from the first network node within a period of time (denoted as time period #1 for distinction), the control node assumes that the first network node agrees with the first orchestration information (equivalent to an implicit response indicating that the first network node agrees with the first orchestration information). As an example, the start time of time period #1 can be the time when the control node sends the first orchestration information. The duration of time period #1 can be predefined or estimated based on historical circumstances and is not limited. As an example, time period #1 can be implemented using a timer.

[0227] As an example, when the first network node disagrees with the first orchestration information, the following implementations may be included.

[0228] In a first possible implementation manner, the control node adjusts the first orchestration information.

[0229] Based on this implementation, after the control node learns that the first network node disagrees with the first orchestration information, it may redetermine the first orchestration information.

[0230] For example, assume that the control node determines an orchestration table for the AI ​​task, where the orchestration table includes orchestration information of N network nodes, where the N network nodes include a first network node. After the control node learns that the first network node disagrees with the first orchestration information, the control node may redetermine the orchestration table.

[0231] In a second possible implementation manner, the first network node adjusts the first orchestration information and sends the adjusted first orchestration information to the control node.

[0232] Based on this implementation, after the first network node disagrees with the first orchestration information, it may adjust the first orchestration information and send the adjusted first orchestration information to the control node.

[0233] For example, assume that the control node determines an orchestration table for the AI ​​task, where the orchestration table includes orchestration information of N network nodes, where the N network nodes include a first network node. As an example, the control node may adjust the orchestration information of at least one network node other than the first network node among the N network nodes based on the adjusted first orchestration information.

[0234] In a third possible implementation, the first network node sends the first task or a portion of the first task to the second network node, where the second network node is at least one network node participating in executing the AI ​​task.

[0235] The second network node may be determined by the first network node, such as an adjacent network node selected by the first network node; or the second network node may be determined by the control node, such as a next network node of the first network node selected by the control node.

[0236] For example, the first network node directly transparently transmits the first task to the second network node, which then executes the first task. For another example, the first network node executes part of the first task and then sends the rest of the first task to the second network node, which then executes the rest of the first task.

[0237] It is understood that the above several possible implementations are exemplary and not limiting. For example, the first network node may first execute part of the first task and then execute the rest of the first task later.

[0238] Optionally, the network node schedules at least one terminal to participate in the operation of the network node, that is, the at least one terminal and the network node collaborate to perform the AI ​​task. In this way, by utilizing at least one terminal to collaboratively perform the AI ​​task, the network node can reduce the overhead incurred by performing the AI ​​task.

[0239] As an example, the at least one terminal may be a terminal for which the network node provides communication services, or a terminal within a cell managed by the network node, or a terminal within the cell of the network node. For example, the network node may schedule the terminals in the cell to participate in operations of the network node.

[0240] For example, taking a first network node as an example, terminals within the first network node's cell include terminal #1 and terminal #2, and the first network node may schedule at least one terminal to participate in operations of the first network node, i.e., to perform a first task. For example, the first network node sends the first task or a portion of the first task to the at least one terminal.

[0241] In one possible implementation, the first network node performs part of the first task, and Terminal #1 and / or Terminal #2 performs the remaining part of the first task. Based on this implementation, as an example, the terminals participating in the execution of the first task may send the processing results of the execution of the first task to the first network node.

[0242] In another possible implementation, terminal #1 and / or terminal #2 executes the first task.

[0243] For example, terminal #1 or terminal #2 executes the complete first task. In this case, as an example, the terminal that executes the complete first task may send the processing result of the first task to the first network node.

[0244] For another example, terminal #1 and terminal #2 each complete the first task. In this case, as an example, terminal #1 and terminal #2 can send the processing results of the first task to the first network node, and the first network node can merge or filter the processing results provided by terminal #1 and terminal #2.

[0245] For another example, terminal #1 executes part of a first task, and terminal #2 executes the rest of the first task. In this case, as an example, terminal #1 and terminal #2 can send the processing results of the first task to the first network node, and the first network node can merge or filter the processing results provided by terminal #1 and terminal #2.

[0246] Optionally, the network node determines whether the terminal participates in executing the AI ​​task according to the AI ​​state of the terminal, which will be described in detail later in conjunction with method 500.

[0247] It will be appreciated that the above method 300 is primarily described with respect to a control node determining the orchestration information of a network node for an AI task, and is not intended to be limiting. In one example, the control node may also determine the orchestration information of at least one core network node for an AI task, i.e., the at least one core network node may collaborate to execute the AI ​​task based on their respective orchestration information. In another example, the control node may also determine the orchestration information of at least one terminal for an AI task, i.e., the at least one terminal may collaborate to execute the AI ​​task based on their respective orchestration information.

[0248] 4 , as an example, is a schematic diagram of a method 400 for AI task indication provided by another embodiment of the present application. The method 400 may include the following steps.

[0249] 410. The first network node sends a processing result and target state information of a first AI task to the second network node.

[0250] The target state information is used to indicate the target result of the AI ​​task, or in other words, the target state information is used to indicate the final state of the AI ​​task.

[0251] For example, in the case of a model-related AI task, target state information indicates the model's final state, or describes the state of the model when it stops flowing in the network. For example, target state information includes at least one of the following: accuracy, timeliness, and model structure. Accuracy can indicate the model's performance when performing various tasks, while timeliness can indicate the time it took to generate the model.

[0252] For another example, taking an AI task involving a dataset, the target state information indicates the final state of the dataset, or can be used to describe the state of the dataset when it stops flowing in the network. For example, the target state information includes at least one of the following: accuracy, timeliness, composition, and attributes. Accuracy can characterize the performance of a dataset under several test models. Timeliness can characterize the generation time of a dataset. Composition can characterize the composition of the data contained in the dataset. Attributes can characterize the type, quantization, and dimensionality of the data contained in the dataset.

[0253] Optionally, method 400 further includes step 420 .

[0254] 420. The second network node executes a second task of the AI ​​task based on the processing result of the first task and the target state information.

[0255] The processing result and target state information of the first task can implicitly instruct the second network node to participate in executing the AI ​​task, such as the second network node executing the second task of the AI ​​task. In other words, after receiving the processing result and target state information of the first task, the second network node can know that it will participate in executing the AI ​​task.

[0256] Based on the embodiments of the present application, network nodes can collaborate to perform AI tasks and determine whether to participate in the execution of AI tasks based on current processing results and target status information.

[0257] As an example, the processing result of the first task represents the current state information of the AI ​​task. The current state information is used to indicate the current result of the AI ​​task, or in other words, the current state information is used to indicate the current state of the AI ​​task. In one possible scenario, the second network node receives the current state information and target state information of the AI ​​task. Based on the inconsistency between the current state information and the target state information, the second network node determines to participate in the execution of the AI ​​task. The second network node may execute the AI ​​task with the target state information as the final result of the AI ​​task.

[0258] For example, in the case of a model-related AI task, the current state information indicates the current state of the model, i.e., the state of the model when it was generated by the first network node. For example, the current state information includes at least one of the following: accuracy, timeliness, and model structure. For a description of each piece of information, please refer to the relevant description in step 410 and will not be repeated here.

[0259] For another example, consider an AI task involving a dataset. Current state information indicates the current state of the dataset, specifically the state of the dataset at the time the first network node generated it. For example, current state information includes at least one of the following: accuracy, timeliness, composition, and attributes. For a description of each piece of information, refer to the relevant description in step 410 and will not be repeated here.

[0260] Optionally, in step 410, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node, including: based on the AI ​​capability of the second network node, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node.

[0261] For example, if the first network node learns that the second network node supports the AI ​​task based on the AI ​​capability of the second network node, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node.

[0262] For another example, if the first network node learns, based on the AI ​​capabilities of the second network node, that the computing power supported by the second network node meets a preset value, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node. The preset value can be predefined, such as by a protocol, or estimated based on historical circumstances, without limitation.

[0263] For another example, if the first network node learns, based on the AI ​​capabilities of the second network node, that the performance of the second network node's local AI model meets a preset condition, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node. The preset condition can be predefined, such as by a protocol, or estimated based on historical circumstances, without limitation.

[0264] Regarding the first network node and the second network node, any one of the following may be satisfied.

[0265] In one example, the first network node and the second network node are adjacent network nodes, wherein the adjacent network nodes may be, for example, network nodes that are adjacent in location, or network nodes that have an adjacent relationship in a network topology structure.

[0266] In another example, the relative position between the first network node and the second network node satisfies a preset condition. The relative position between the first network node and the second network node can be understood as the position of the second network node relative to the first network node, or can also be described as the position of the first network node relative to the second network node, relative to the second network node. The relative position can include distance and / or angle.

[0267] It is understood that the above description of the first network node and the second network node is for illustrative purposes only, and the embodiments of the present application are not limited thereto. For example, the second network node is a network node that can provide services to the terminal. Specifically, the first network node can also obtain the AI ​​capabilities of the second network node that can provide services to the terminal after receiving the task request for the AI ​​task from the terminal. For another example, the second network node can be a network node that previously collaborated with the first network node to perform the AI ​​task. For another example, the second network node can be any network node.

[0268] The first network node may obtain the AI ​​capability of the second network node in any of the following ways.

[0269] In a first possible implementation manner, the first network node obtains the AI ​​capability of the second network node from the control node.

[0270] In one example, a first network node queries its control node for the AI ​​capabilities of a second network node. For example, the first network node sends a first request message to the control node, requesting the AI ​​capabilities of the second network node. Based on the request of the first network node, the control node sends a response message to the first request message, indicating the AI ​​capabilities of the second network node. The response message indicating the AI ​​capabilities of the second network node can be a direct indication, such as including the AI ​​capabilities of the second network node in the response message, or an indirect indication, such as including other information in the response message, and the AI ​​capabilities of the second network node can be indirectly obtained based on the other information.

[0271] For example, when a first network node is unable to complete an AI task, it may query the control node for the AI ​​capabilities of a second network node. This allows the decision to obtain the AI ​​capabilities of the second network node from the control node based on the actual situation. For example, if the AI ​​capabilities of the first network node are unable to complete the AI ​​task, the first network node may request other network nodes (such as the second network node) to collaborate to complete the AI ​​task. Therefore, the first network node may obtain the AI ​​capabilities of the second network node from the control node, so that the second network node can be determined based on its AI capabilities whether it can collaborate to complete the AI ​​task.

[0272] In another example, a first network node subscribes to the AI ​​capabilities of a second network node from a control node. For example, the first network node subscribes to the AI ​​capabilities of the second network node from the control node. After learning the AI ​​capabilities of the second network node, the control node sends the AI ​​capabilities of the second network node to the first network node in response to the first network node's subscription. In other words, the first network node first obtains the AI ​​capabilities of the second network node from the control node and saves them. This allows the first network node to directly use the AI ​​capabilities of the second network node after determining an AI task, reducing the latency associated with executing the AI ​​task.

[0273] In a second possible implementation manner, the first network node obtains the AI ​​capability of the second network node from the second network node.

[0274] In one example, a first network node queries a second network node for the second network node's AI capabilities. For example, the first network node sends a first request message to the second network node, where the first request message is used to request the second network node's AI capabilities. Based on the first network node's request, the second network node sends a response message to the first network node, where the response message indicates the second network node's AI capabilities.

[0275] In another example, the first network node subscribes to the second network node for the AI ​​capability of the second network node.

[0276] Regarding the above two examples, please refer to the description in the first possible implementation method above, which will not be repeated here.

[0277] It will be understood that the above implementation is for illustrative purposes only and the embodiments of the present application are not limited thereto. For example, the control node may proactively send the AI ​​capabilities of the second network node to the first network node. For another example, the first network node may obtain the AI ​​capabilities of the second network node from other network nodes or a core network node.

[0278] Optionally, before step 410, method 400 further includes: the first network node sending a second request message to the second network node, the second request message requesting the second network node to collaborate in executing the AI ​​task. Based on this, if the first network node determines that the second network node agrees to collaborate in executing the AI ​​task, the first network node sends the processing result and target state information of the first AI task to the second network node.

[0279] For example, the first network node sends a second request message to the second network node. If the first network node receives a response to the second request message from the second network node, where the response to the second request message indicates that the second network node agrees to collaborate in executing the AI ​​task, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node.

[0280] For another example, the first network node sends a second request message to the second network node. If the first network node does not receive a negative response from the second network node within a period of time (for distinction, recorded as time period #2), the first network node assumes that the second network node agrees to collaborate in performing the AI ​​task (equivalent to an implicit response message indicating that the second network node agrees to collaborate in performing the AI ​​task). Therefore, the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node. As an example, the starting time of time period #2 can be the time when the first network node sends the second request message, and the duration of time period #2 can be predefined, or it can be estimated based on historical circumstances and is not restricted. As an example, time period #2 can be implemented by a timer.

[0281] Optionally, the method 400 further includes: the first network node sending area information to the second network node, where the area information is used by the second network node to determine a network node that collaborates to execute the AI ​​task.

[0282] The region information is used to assist the current network node in determining other nodes that can collaborate to perform AI tasks. For example, the region information sent by the first network node to the second network node is used to assist the second network node in determining other network nodes that can collaborate to perform AI tasks.

[0283] As an example, regional information may include geographic location information, or regional information may also be embodied by some parameters (for distinction, denoted as parameter #A), and the parameter #A may be, for example: service type, terminal type, node computing power type. Among them, the service type may be the service type supported or running in a certain area. The terminal type may be the terminal type in a certain area. The node type may be the computing power type of the node in a certain area. Generally speaking, the parameter #A of nodes in the same area is relatively close. When selecting a node, by referring to the parameter #A of each area, the appropriate next node can be selected according to actual needs. For example, when the second network node selects the next network node, it may select a network node in an area where the difference in parameter #A is relatively large, or it may select a network node in an area where the difference in parameter #A is relatively close.

[0284] Optionally, the network node schedules at least one terminal to participate in the network node's operations. Specifically, at least one terminal collaborates with the network node to perform the AI ​​task. By utilizing at least one terminal to collaboratively perform the AI ​​task, the network node's overhead associated with performing the AI ​​task can be reduced. For details, please refer to the relevant description in method 300 and will not be repeated here. Furthermore, the network node optionally determines whether the terminal participates in the AI ​​task based on the terminal's AI status. This will be described in detail later in conjunction with method 500.

[0285] It will be appreciated that the above method 400 is primarily described with respect to the collaborative execution of an AI task between multiple network nodes, and is not intended to be limiting. In one example, a network node may also collaborate with a terminal to execute an AI task. For example, a first network node sends the processing result and target state information of a first task of an AI task to at least one terminal. In another example, a network node may also collaborate with a core network node to execute an AI task. For example, the first network node sends the processing result and target state information of the first task of an AI task to at least one core network node.

[0286] 5 , as an example, is a schematic diagram of a method 500 for AI task indication provided by another embodiment of the present application. The method 500 may include the following steps.

[0287] 510. The network node sends an AI task to a terminal, wherein the terminal is in a preset state.

[0288] Optionally, method 500 further includes step 520 .

[0289] 520, the terminal executes the AI ​​task.

[0290] Based on this, by defining different states for terminals (referred to as AI states for differentiation), network nodes can determine whether a terminal can participate in AI tasks based on its state. For example, a network node can send an AI task to a terminal in a preset state, indicating that the AI ​​in the preset state can participate in the AI ​​task.

[0291] Further optionally, if the state of the terminal is not a preset state, the network node sends a notification message to the terminal, and the notification message notifies that the terminal is adjusted to the preset state, that is, the notification message notifies that the AI ​​state of the terminal is adjusted to the preset state. As an example, the notification message may be a combination of any one or more of the following: radio resource control signaling, MAC layer signaling, physical layer signaling, and AI paging. Among them, the radio resource control signaling, for example, includes RRC signaling, the MAC layer signaling, for example, includes MAC CE, and the physical layer signaling, for example, includes DCI. Among them, the AI ​​paging can be sent by the network node to trigger a specific terminal, or a terminal in a specific AI state, to perform an AI state transition.

[0292] As an example, the AI ​​state of the terminal can be any of the following: AI-idle state, AI-activated state, and AI-suspended state. The preset state can be, for example, AI-activated state. The names of the various AI states are merely examples and do not limit the scope of protection of the embodiments of this application.

[0293] 1) AI-Idle: The terminal has not established a connection with the AI ​​node and there is no AI model locally. If the terminal is in the AI-Idle state, it can perform operations such as AI paging monitoring, AI node selection, and AI connection establishment.

[0294] For example, if a terminal is in the AI-idle state, the network node may first trigger the terminal to transition to the AI-active state and then schedule the terminal to participate in the AI ​​task. As an example, the network node triggers the terminal to complete the AI ​​state transition through signaling, such as sending a notification message to the terminal.

[0295] 2) AI-Active: The terminal has established an AI connection with the AI ​​node. If the terminal is in the AI-Active state, it can perform operations such as AI scheduling monitoring, executing AI tasks according to the schedule, and selecting AI nodes.

[0296] For example, if the terminal is in the AI-activated state, the network node may schedule the terminal to participate in executing the AI ​​task.

[0297] 3) AI-Persistent State: The terminal has not established an AI connection with the AI ​​node, and the AI ​​model is deployed locally. If the terminal is in the AI-Persistent state, the terminal can perform operations such as AI paging monitoring, AI node selection, and AI connection establishment.

[0298] For example, if the terminal is in the AI-stay state, the network node may first trigger the terminal to transition to the AI-active state and then schedule the terminal to participate in the AI ​​task. As an example, the network node triggers the terminal to complete the AI ​​state transition through signaling, such as sending a notification message to the terminal.

[0299] It is understood that the above is an exemplary description and is not intended to limit the scope of the present invention. For example, in step 510, the control node sends the AI ​​task to the terminal.

[0300] It is also understood that the above description of the AI ​​state of the terminal is merely exemplary and not limiting. For example, the AI ​​state of the terminal may include other AI states in addition to the above AI-idle state, AI-activated state, and AI-stayed state.

[0301] It can also be understood that the method 500 can be used alone or in combination with the foregoing method 300 or method 400, without limitation thereto.

[0302] For example, method 500 can be used in conjunction with method 300. For example, using a first network node as an example, the first network node sends a first task or a portion of the first task to at least one terminal, where the state of the at least one terminal is a preset state. Based on this, if the state of the terminal is the preset state, the first network node sends the first task or the portion of the first task to the terminal, and the terminal cooperates with the first network node to execute the first task.

[0303] As another example, method 500 can be used in conjunction with method 400. For example, taking a first network node as an example, the first network node sends a first task or a portion of the first task to at least one terminal, and the state of the at least one terminal is a preset state. Based on this, if the state of the terminal is the preset state, the first network node sends the first task or the portion of the first task to the terminal, and the terminal cooperates with the first network node to execute the first task.

[0304] For ease of understanding, the following examples illustrate embodiments of the present application using a RAN as the network node and an AI-MF as the control node, with reference to Figures 6 to 9. The steps and terms involved may be specifically described above.

[0305] Referring to Figure 6 , as an example, Figure 6 is a schematic flowchart of a method 600 for indicating an AI task, according to an embodiment of the present application. This method 600 can be used to implement a solution such as method 400 . This method 600 is applicable to scenarios where a terminal requests a model-related AI task from the RAN. As an example, this method 600 may include the following steps.

[0306] 601. The AI-MF maintains the AI ​​capability of at least one RAN.

[0307] The RAN's AI capabilities may include at least one of the following: RAN priority, computing power supported by the RAN, RAN hardware capabilities, AI tasks supported by the RAN (or the types of operations that the RAN can perform), performance of the RAN's local AI model, and performance of the RAN's local dataset. Optionally, if the RAN's AI capabilities include AI tasks supported by the RAN, the RAN's AI capabilities also include parameters associated with the AI ​​tasks supported by the RAN.

[0308] For example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include model training, then the RAN's AI capabilities may further optionally include parameters associated with model training. For example, the parameters associated with model training include at least one of the following: model structure, training set, and available computing power.

[0309] For another example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include model fusion, then the RAN's AI capabilities may further optionally include parameters associated with model fusion. For example, the parameters associated with model fusion include at least one of the following: a model fusion strategy, a model structure supporting fusion, and local knowledge base information.

[0310] For another example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include model testing, then the RAN's AI capabilities may further optionally include parameters associated with the model testing. For example, the parameters associated with the model testing may include at least one of the following: model testing capabilities and test sets.

[0311] As an example, the AI ​​capabilities of the RAN may be present in the form of a table, a function, or a string, such as for storage or transmission. Table 3 below is an example of presenting the AI ​​capabilities of the RAN in table form.

[0312] Table 3

[0313]

[0314] Taking Table 3 as an example, for RAN#1, the AI ​​tasks it supports include Task A. When RAN#1's local model executes Task A, its accuracy is value 1 and its timeliness is value 2. Accuracy represents the model's performance when executing multiple tasks, while timeliness represents the time it takes to generate the model.

[0315] In one example, an AI task supported by the RAN can be represented by at least one bit. Taking model-related AI tasks as an example, for example, assuming that model-related AI tasks include: model training tasks, model testing tasks, and model fusion tasks, and assuming that the AI ​​tasks supported by the RAN are 2 bits. If the bit is set to "00", it means that the AI ​​task supported by the RAN is a model training task; if the bit is set to "01", it means that the AI ​​task supported by the RAN is a model testing task; if the bit is set to "10", it means that the AI ​​task supported by the RAN is a model fusion task. It should be understood that the above is merely an exemplary description and is not limiting.

[0316] In another example, the AI ​​tasks supported by the RAN can be represented by a bitmap. Taking model-related AI tasks as an example, for example, assuming that the model-related AI tasks include: model training tasks, model testing tasks, and model fusion tasks, and a bit value of "1" indicates support, and a bit value of "0" indicates non-support. For example, if the AI ​​tasks supported by the RAN are represented as "110", the three bits in "110" correspond to the model training task, model testing task, and model fusion task, respectively. Therefore, "110" indicates that the RAN supports the model training task and the model testing task, but does not support the model fusion task. For another example, if the AI ​​tasks supported by the RAN are represented as "101", the three bits in "101" correspond to the model training task, model testing task, and model fusion task, respectively. Therefore, "101" indicates that the RAN supports the model training task and the model fusion task, but does not support the model testing task. It will be understood that the above examples are illustrative and the embodiments of the present application are not limited thereto.

[0317] It should be understood that Table 3 is merely illustrative and not limiting. Any variations of Table 3 are applicable to this application. For example, Table 3 may include a greater number of RANs. For another example, RAN#1 and RAN#2 in Table 3 support a greater number of AI tasks. For another example, Table 3 may also include a greater number of parameters characterizing the performance of the local AI model.

[0318] In the embodiments of the present application, model-related AI tasks are mainly used as examples for illustrative explanation. Therefore, the above-mentioned AI capabilities of RAN mainly introduce model-related capabilities and are not limited to them.

[0319] In the embodiment of the present application, it is assumed that the terminal publishes an AI task to the first RAN, and the AI ​​task published by the terminal to the first RAN is a model training task.

[0320] 602. The terminal sends relevant information of the initial model to the first RAN.

[0321] For example, the terminal performs an encapsulation operation on the initial model, and carries relevant information of the initial model in the encapsulation. Optionally, the terminal may also perform a segmentation operation on the initial model, so as to facilitate the first RAN to correctly restore the initial model.

[0322] The initial model is the model to be trained.

[0323] The information related to the initial model may include at least one of the following: a parameter set of the initial model, current state information, target state information, region information, and a version of the initial model. The following briefly describes each of the above information. For details not described in detail, please refer to the relevant description of method 400 above.

[0324] 1) Current state information, which describes the state of the model at the time the current node was generated. For example, this information may include at least one of the following: accuracy and timeliness. For operations involving structural changes to the model, such as model compression and distillation, a description of the model structure may also be included in the state information.

[0325] It is understandable that the initial model may not carry the current state information.

[0326] 2) Target state information, or the target state information of the initial model, can be used to describe the final state of the model, or the state of the model when it stops flowing in the network. For example, target state information includes at least one of the following: accuracy and timeliness. For operations involving model structure changes, such as model compression and model distillation, a description of the model structure can also be added to the state information.

[0327] 3) Regional information, used to assist the current node in deciding which other nodes to collaborate with to perform the model training task. For example, regional information in the initial model information can be used to assist the first RAN node in deciding which RAN to collaborate with to perform the model training task.

[0328] 4) The parameter set of the initial model may include the training weights of the neural network corresponding to the initial model.

[0329] 5) The version of the initial model, such as t1, indicates that the initial model provided by the terminal has been trained t1 times, where t1 is an integer greater than or equal to 0. For example, if the version of the initial model is 0, it indicates that the initial model provided by the terminal has not been trained. For another example, if the version of the initial model is 1, it indicates that the initial model provided by the terminal has been trained once (for example, the terminal has already performed model training once).

[0330] It is understood that the above information is for illustrative purposes only and is not intended to be limiting. For example, the relevant information of the initial model may also include: the structure of the neural network corresponding to the initial model, the calculation rules of the initial model parameters, the number of the initial model, etc.

[0331] Regarding step 602, the following implementation methods may be included.

[0332] In one possible implementation, in step 602, the terminal sends information related to the initial model to the first RAN. The information related to the initial model may implicitly indicate to the first RAN that model training is required for the initial model. For example, the information related to the initial model includes current state information and target state information. The first RAN determines to perform model training on the initial model based on an inconsistency between the current state information and the target state information.

[0333] In another possible implementation, in step 602, the terminal sends indication information and relevant information of the initial model to the first RAN, where the indication information instructs to perform model training on the initial model.

[0334] 603 : The first RAN performs model training on the initial model to obtain a first model.

[0335] The first RAN may perform a model training task based on the initial model provided by the terminal in step 602. For the sake of distinction, a model obtained by the first RAN performing model training on the initial model is recorded as the first model.

[0336] In this embodiment of the present application, it is assumed that the first RAN cannot complete the model training task alone. In other words, the state of the first model obtained by the first RAN through model training of the initial model does not meet the target state required by the terminal. Therefore, the first RAN can complete the model training task with the cooperation of another RAN. It is assumed that the RAN determined by the first RAN to cooperate in performing the model training task is the second RAN.

[0337] Optionally, the first RAN may also schedule terminals in the cell to participate in operations, such as participating in model training of the initial model. For specific implementation, please refer to the relevant description in method 500, which will not be repeated here.

[0338] 604. The first RAN obtains the AI ​​capability of the second RAN from the AI-MF.

[0339] Assuming that the at least one RAN in step 601 includes a second RAN, that is, the AI-MF maintains the AI ​​capability of the second RAN, the first RAN may obtain the AI ​​capability of the second RAN from the AI-MF.

[0340] Regarding the first RAN and the second RAN, reference may be made to the description of the first network node and the second network node in the above method 400 , which will not be repeated here.

[0341] Regarding the first RAN acquiring the AI ​​capability of the second RAN from the AI-MF, reference may be made to the description of the first network node acquiring the AI ​​capability of the second network node from the control node in the previous method 400, which is not repeated here.

[0342] It is understood that the embodiments of the present application are mainly described using one second RAN as an example, and the number of second RANs is not limited. For example, the first RAN can obtain the AI ​​capabilities of at least one second RAN from the AI-MF.

[0343] It should also be understood that step 604 is merely an example and the embodiments of the present application are not limited thereto. For example, the first RAN may also obtain the AI ​​capabilities of the second RAN from the second RAN. For details, please refer to the description of the first network node obtaining the AI ​​capabilities of the second network node from the second network node in the above method 400, which will not be repeated here.

[0344] 605 : The first RAN sends relevant information of the first model to the second RAN.

[0345] For example, the first RAN may encapsulate the first model, carrying relevant information of the first model in the encapsulation. Optionally, the first RAN may also segment the first model, thereby facilitating the second RAN to correctly restore the first model.

[0346] The first model is a model obtained after the first RAN performs model training.

[0347] The relevant information of the first model may include at least one of the following: a parameter set of the first model, current state information, target state information, region information, and a version of the first model. The following briefly describes the current state information, region information, and version of the first model. For other information not described in detail, please refer to the relevant description in step 602.

[0348] 1) Current state information: As mentioned above, the current state information is used to describe the state of the model when the current node is generated. Therefore, the current state information provided by the first RAN to the second RAN here represents the current state information of the first model, which is used to describe the state of the first model when it was generated by the first RAN.

[0349] 2) Regional information: As mentioned above, regional information is used to assist the current node in deciding which other nodes to collaborate with to perform the model training task. Therefore, the regional information in the relevant information of the first model here can be used to assist the second RAN in deciding which RAN to collaborate with to perform the model training task.

[0350] The region information in the relevant information of the first model and the region information in the relevant information of the initial model in step 602 may be the same as or different from each other.

[0351] For example, the area information in the relevant information of the first model is the same as the area information in the relevant information of the initial model, for example, both are area information where the terminal can receive signals.

[0352] For another example, the regional information in the relevant information of the first model is different from the regional information in the relevant information of the initial model. The regional information in the relevant information of the first model is the information of the low-frequency base station coverage area, and the regional information in the relevant information of the initial model is the information of the high-frequency base station coverage area.

[0353] 3) The version of the first model, such as t2, indicates that the first model provided by the first RAN has been trained t2 times, where t2 is an integer greater than or equal to 1. For example, a first model version of 1 indicates that the first model provided by the first RAN has been trained once. In other words, the first model is the model that has been trained once on the initial model, or the first RAN is the RAN that performed model training on the initial model for the first time.

[0354] The first RAN may send the relevant information of the first model to the second RAN in the following two ways:

[0355] In one possible implementation, if the first RAN determines that the second RAN can perform the model training task, the first RAN sends the relevant information of the first model to the second RAN. For example, the first RAN determines that the second RAN can perform the model training task based on the AI ​​capabilities of the second RAN obtained in step 604, such as if the AI ​​capabilities of the second RAN include AI tasks supported by the second RAN, and the AI ​​tasks supported by the second RAN include model training tasks, and therefore the first RAN sends the relevant information of the first model to the second RAN.

[0356] In another possible implementation, after the first RAN trains the initial model, it directly sends the relevant information of the first model to the second RAN. For example, the first RAN may default or assume that the second RAN can perform model training tasks, and therefore, after training the initial model, it directly sends the relevant information of the first model to the second RAN.

[0357] Optionally, the first RAN sends relevant information of the first model to the second RAN, including: when the first RAN determines that the second RAN agrees to collaborate in performing the model training task, the first RAN sends relevant information of the first model to the second RAN.

[0358] For example, before step 605, method 600 further includes: the first RAN requests the second RAN to perform the model training task. After receiving confirmation from the second RAN, i.e., agreeing to cooperate with the first RAN to perform the model training task, the first RAN sends relevant information of the first model to the second RAN.

[0359] 606 : The second RAN performs model training on the first model to obtain a second model.

[0360] The second RAN can perform the model training task based on the first model generated by the first RAN. For the sake of distinction, the model obtained by the second RAN through model training of the first model is recorded as the second model.

[0361] In a first possible scenario, after the second RAN performs the model training task, the model reaches the target state, that is, the state of the second model meets the target state, and the method 600 further includes step 607 .

[0362] In the second possible scenario, after the second RAN completes the model training task, the model fails to reach the target state. This means that the second model's state does not meet the target state. The second RAN can then obtain the AI ​​capabilities of the third RAN and send relevant information about the second model to the third RAN. For details, see steps 604 and 605, which are not detailed here. This process continues in this manner until the model reaches the target state and the final model is sent to the terminal.

[0363] Optionally, the second RAN may also schedule terminals in the cell to participate in operations, such as participating in model training of the first model. For specific implementation, please refer to the relevant description in method 500, which will not be repeated here.

[0364] 607 : The second RAN sends the second model to the terminal.

[0365] Assuming that after the second RAN performs the model training task, the model reaches the target state, that is, the state of the second model meets the target state, in one possible implementation, the second RAN sends the second model to the terminal; or in another possible implementation, the second RAN sends the second model to the first RAN, and the first RAN forwards the second model to the terminal, without limitation.

[0366] As shown in Figure 7 , which is a schematic diagram applicable to an embodiment of the present application, number i (i=1, 2, 3, 4, 5, ..., N) represents a different RAN, and N is an integer greater than 1.

[0367] For example, a terminal sends information about an initial model to a first RAN (e.g., RAN numbered 1). The first RAN performs model training on the initial model to obtain a first model, and then sends information about the first model, such as regional information, current model state (i.e., state description information of the first model), target model state (i.e., target state information), and model version 1, to a second RAN (e.g., RAN numbered 2). The second RAN performs model training on the first model to obtain a second model, and then sends information about the second model, such as regional information, current model state (i.e., state description information of the second model), target model state (i.e., target state information), and model version 2, to a third RAN (e.g., RAN numbered 3). This continues in this manner until the current model state reaches the target model state. Model version 1 indicates that the model provided by the first RAN is the model obtained by performing the first model training on the initial model, or in other words, the first RAN is the RAN that first performed model training on the initial model. Model version 2 indicates that the model provided by the second RAN is the model obtained by performing the second model training on the initial model, or in other words, the second RAN is the RAN that secondly performed model training on the initial model.

[0368] It is understandable that method 600 is mainly illustrated by taking the model training task as an example. It is understandable that the above-mentioned model training task can be replaced by any other model-related tasks.

[0369] It can also be understood that the above steps are merely illustrative and are not strictly limited to this. In addition, the size of the sequence numbers of the above processes does not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. For example, there is no strict order between step 604 and step 602. For example, step 604 can be executed first, and then step 602; or step 602 can be executed first, and then step 604; or they can be performed simultaneously, and there is no limitation on this.

[0370] It is also understood that the above description mainly uses the example of one RAN determining the next collaborative RAN as an example, and is not limited to this. For example, one RAN can determine multiple collaborative RANs, and the multiple collaborative RANs can collaborate to perform AI tasks.

[0371] The above, combined with Figure 6, illustrates a scenario where a terminal requests a model-related AI task from a RAN. Based on the above embodiment, multiple RANs can collaborate to complete the AI ​​task requested by the terminal. Furthermore, each RAN can collaborate to execute the AI ​​task based on the model-related information received from the previous RAN.

[0372] Referring to Figure 8 , as an example, Figure 8 is a schematic flowchart of a method 800 for indicating an AI task, according to another embodiment of the present application. This method 800 can be used to implement a solution such as method 400 . This method 800 is applicable to scenarios where a terminal requests an AI task related to a dataset from the RAN. As an example, this method 800 may include the following steps.

[0373] 801. The AI-MF maintains the AI ​​capability of at least one RAN.

[0374] The RAN's AI capabilities may include at least one of the following: RAN priority, computing power supported by the RAN, RAN hardware capabilities, AI tasks supported by the RAN (or the types of operations that the RAN can perform), performance of the RAN's local AI model, and performance of the RAN's local dataset. Optionally, if the RAN's AI capabilities include AI tasks supported by the RAN, the RAN's AI capabilities also include parameters associated with the AI ​​tasks supported by the RAN.

[0375] For example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include data cleansing operations, then the RAN's AI capabilities may further optionally include parameters associated with the data cleansing operations. For example, the parameters associated with the data cleansing operations include at least one of the following: data supplementation for specific attributes, redundancy identification, and authenticity verification.

[0376] For another example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include data augmentation operations, then the RAN's AI capabilities may further optionally include parameters associated with the data augmentation operations. For example, the parameters associated with the data augmentation operations include supported augmentation strategies, such as data augmentation for a single data source (single-sample augmentation, multi-sample augmentation, generative adversarial network (GAN) generation, automatic augmentation, etc.), and data integration for multiple data sources.

[0377] For another example, if the RAN's AI capabilities include AI tasks supported by the RAN, and the AI ​​tasks supported by the RAN include data reduction operations, then the RAN's AI capabilities may further optionally include parameters for the data reduction operations. For example, the parameters associated with the data reduction operations include the reduction strategy employed, such as dimensionality reduction or dimensionality transformation for a specific task.

[0378] As an example, the AI ​​capabilities of the RAN may be present in the form of a table, a function, or a string, such as for storage or transmission. Table 4 below is an example of presenting the AI ​​capabilities of the RAN in table form.

[0379] Table 4

[0380]

[0381]

[0382] It can be understood that the difference between Table 4 and Table 3 is that Table 3 mainly uses model-related AI tasks as an example, while Table 4 mainly uses dataset-related AI tasks as an example.

[0383] Taking Table 4 as an example, for RAN#1, the AI ​​tasks supported by RAN#1 include Task A, and Task A's accuracy is value 1, and its timeliness is value 2. Accuracy represents the performance of a dataset under the test model, and timeliness represents the time it takes to generate the dataset.

[0384] In one example, the AI ​​tasks supported by the RAN can be represented by at least one bit. Taking AI tasks related to a data set as an example, for example, assuming that the AI ​​tasks related to the data set include: data cleaning, data augmentation, data reduction, and data conversion, and assuming that the AI ​​tasks supported by the RAN are 2 bits. If the bit is set to "00", it means that the AI ​​task supported by the RAN is data cleaning; if the bit is set to "01", it means that the AI ​​task supported by the RAN is data augmentation; if the bit is set to "10", it means that the AI ​​task supported by the RAN is data reduction; if the bit is set to "11", it means that the AI ​​task supported by the RAN is data conversion. It should be understood that the above is merely an exemplary description and is not limiting.

[0385] As another example, AI tasks supported by the RAN can be represented by a bitmap. Taking dataset-related AI tasks as an example, assume that the dataset-related AI tasks include data cleansing, data augmentation, data reduction, and data conversion, with a bit value of "1" indicating support and a bit value of "0" indicating non-support. For example, if the AI ​​tasks supported by the RAN are represented as "0110," the four bits in "0110" correspond to data cleansing, data augmentation, data reduction, and data conversion, respectively. Therefore, "0110" indicates that the RAN supports data augmentation and data reduction, but does not support data cleansing and data conversion. For another example, if the AI ​​tasks supported by the RAN are represented as "1011," the four bits in "1011" correspond to data cleansing, data augmentation, data reduction, and data conversion, respectively. Therefore, "1011" indicates that the RAN supports data cleansing, data reduction, and data conversion, but does not support data augmentation. It should be understood that the above examples are illustrative and the embodiments of the present application are not limited thereto.

[0386] It should be understood that Table 4 is merely illustrative and not limiting. Any variations of Table 4 are applicable to this application. For example, Table 4 may include a greater number of RANs. For another example, RAN#1 and RAN#2 in Table 4 may support different AI tasks, or RAN#1 and RAN#2 may support a greater number of AI tasks. For another example, Table 4 may include a greater number of parameters characterizing the performance of a local dataset.

[0387] In the embodiments of the present application, AI tasks related to data sets are mainly used as examples for illustrative description. Therefore, the above-mentioned AI capabilities of RAN mainly introduce capabilities related to data sets and are not limited to this.

[0388] In the embodiment of the present application, it is assumed that the terminal issues an AI task to the first RAN, and the AI ​​task issued by the terminal to the first RAN is data augmentation.

[0389] 802. The terminal sends relevant information of the initial data set to the first RAN.

[0390] The initial dataset is the dataset for the data augmentation task to be performed.

[0391] The information related to the initial dataset may include at least one of the following: current state information, target state information, region information, and version of the initial dataset. The following briefly introduces each of the above information.

[0392] 1) Current state information, which can be used to describe the state of a dataset at the time of generation at the current node. For example, this current state information may include at least one of the following: accuracy, timeliness, composition, and attributes. Accuracy can characterize the performance of a dataset under several test models. Timeliness can characterize the generation time of a dataset. Composition can characterize the composition of the data contained in the dataset. Attributes can characterize the type, quantization, and dimensionality of the data contained in the dataset.

[0393] It is understandable that the initial data set may not carry the current state information.

[0394] 2) Target state information, or the target state information of the initial dataset, can be used to describe the final state of the dataset, or the state of the dataset when it stops flowing in the network. For example, target state information includes at least one of the following: accuracy, timeliness, composition, and attributes. For details on each of these information, please refer to the previous description and will not be repeated here.

[0395] 3) Regional information, used to assist the current node in deciding which other nodes to collaborate with to perform the dataset augmentation task. For example, regional information in the relevant information of the initial dataset can be used to assist the first RAN node in deciding which RAN to collaborate with to perform the data augmentation task.

[0396] 5) The version of the initial dataset, such as t1, indicates that the initial dataset provided by the terminal has been augmented t1 times, where t1 is an integer greater than or equal to 0. For details, please refer to the description of the model version in method 600, which will not be repeated here.

[0397] It will be understood that the above information is for illustrative purposes only and is not intended to be limiting.

[0398] Regarding step 802, the following implementation methods may be included.

[0399] In one possible implementation, in step 802, the terminal sends information related to the initial dataset to the first RAN. The information related to the initial dataset may implicitly indicate that the first RAN needs to perform a dataset augmentation operation on the initial dataset. For example, the information related to the initial dataset includes current state information and target state information. The first RAN determines to perform a dataset augmentation operation on the initial dataset based on an inconsistency between the current state information and the target state information.

[0400] In another possible implementation, in step 802, the terminal sends indication information and relevant information of the initial data set to the first RAN, where the indication information indicates to perform data set expansion on the initial data set.

[0401] 803 : The first RAN performs data amplification on the initial data set to obtain a first data set.

[0402] The first RAN may perform a data augmentation task based on the initial data set provided by the terminal in step 602. For the sake of distinction, a data set obtained by the first RAN performing data augmentation on the initial data set is recorded as a first data set.

[0403] In this embodiment of the present application, it is assumed that the first RAN is unable to complete the data augmentation task alone. In other words, the state of the first data set obtained by the first RAN after data augmentation of the initial data set does not meet the target state required by the terminal. Therefore, the first RAN may collaborate with another RAN to complete the data augmentation task. It is assumed that the RAN determined by the first RAN to collaborate on the data augmentation task is a second RAN.

[0404] Optionally, the first RAN may also schedule terminals in the cell to participate in operations, such as participating in data augmentation of the initial data set. For specific implementation, please refer to the relevant description in method 500, which will not be repeated here.

[0405] 804. The first RAN obtains the AI ​​capability of the second RAN from the AI-MF.

[0406] Assuming that the at least one RAN in step 601 includes a second RAN, that is, the AI-MF maintains the AI ​​capability of the second RAN, the first RAN may obtain the AI ​​capability of the second RAN from the AI-MF.

[0407] Regarding the first RAN and the second RAN, and the manner in which the first RAN obtains the AI ​​capability of the second RAN from the AI-MF, reference may be made to the relevant description in step 601 and will not be repeated here.

[0408] 805 : The first RAN sends relevant information of the first data set to the second RAN.

[0409] The first data set is a data set obtained after the first RAN performs data set amplification.

[0410] The information related to the first dataset may include at least one of the following: current state information, target state information, region information, and the version of the first dataset. The following briefly describes the current state information, region information, and the version of the first model. For other information not described in detail, please refer to the description of step 802.

[0411] 1) Current state information: As mentioned above, the current state information is used to describe the state of the dataset when it was generated at the current node. Therefore, the current state information provided by the first RAN to the second RAN here represents the current state information of the first dataset, which is used to describe the state of the first dataset when it was generated by the first RAN.

[0412] 2) Regional Information: As previously mentioned, regional information is used to assist the current node in determining other nodes with which to collaborate on the data augmentation task. Therefore, the regional information in the relevant information of the first dataset can be used to assist the second RAN in determining a RAN with which to collaborate on the data augmentation task. This regional information can be referenced in step 605 and will not be further described here.

[0413] 3) The version of the first dataset, such as t2, indicates that the first dataset provided by the first RAN has been augmented t2 times, where t2 is an integer greater than or equal to 1. For example, a version of the first dataset of 1 indicates that the first dataset provided by the first RAN has been augmented once. In other words, the first dataset is the dataset that has been augmented once, or the first RAN is the RAN that performed data augmentation on the initial dataset for the first time.

[0414] For a solution of the first RAN sending the relevant information of the first model to the second RAN, reference may be made to the description in step 605 , which will not be repeated here.

[0415] 806 , the second RAN performs data amplification on the first data set to obtain a second data set.

[0416] The second RAN can perform a data augmentation task based on the first data set generated by the first RAN. For the sake of distinction, the data set obtained by the second RAN performing data augmentation on the first data set is recorded as the second data set.

[0417] In a first possible scenario, after the second RAN performs the data augmentation task, the data set reaches the target state, that is, the state of the second data set meets the target state, and the method 800 further includes step 807 .

[0418] In the second possible scenario, after the second RAN performs the data augmentation task, the dataset does not reach the target state. In other words, the state of the second dataset does not meet the target state. The second RAN can then obtain the AI ​​capabilities of the third RAN and send relevant information about the second dataset to the third RAN. For details, refer to steps 804 and 805, which are not detailed here. This process continues in this manner until the dataset reaches the target state and the final dataset is sent to the terminal.

[0419] Optionally, the second RAN may also schedule terminals in the cell to participate in operations, such as participating in data augmentation of the first data set. For specific implementation, please refer to the relevant description in method 500, which will not be repeated here.

[0420] 807 : The second RAN sends a second data set to the terminal.

[0421] Assuming that after the second RAN performs the data augmentation task, the data set reaches the target state, that is, the state of the second data set meets the target state, then in one possible implementation, the second RAN sends the second data set to the terminal; or in another possible implementation, the second RAN sends the second data set to the first RAN, and the first RAN forwards the second data set to the terminal, without limitation.

[0422] It is understandable that the method 800 is mainly illustrated by taking a dataset-related task as an example. It is understandable that the above-mentioned data augmentation task can be replaced by any other dataset-related task.

[0423] It can also be understood that the above steps are merely illustrative and are not strictly limited to this. In addition, the size of the sequence numbers of the above processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. For example, there is no strict order between step 804 and step 802. For example, step 804 can be executed first, and then step 802; or step 802 can be executed first, and then step 804; or they can be performed simultaneously, and there is no limitation on this.

[0424] It is also understood that the above description mainly uses an example of one RAN determining the next cooperating RAN as an example, and is not limited to this. For example, one RAN can determine multiple cooperating RANs, and the multiple cooperating RANs can collaborate to perform AI tasks.

[0425] The above, combined with Figure 8, illustrates a scenario in which a terminal requests an AI task related to a dataset from a RAN. Based on this embodiment, multiple RANs can collaborate to complete the AI ​​task requested by the terminal. Furthermore, each RAN can collaborate to execute the AI ​​task based on the relevant information about the dataset received from the previous RAN.

[0426] Referring to Figure 9 , as an example, Figure 9 is a schematic flowchart of a method 900 for AI task indication according to another embodiment of the present application. Method 900 can be used to implement a solution such as method 300 . Method 900 can be applicable to scenarios where a terminal initiates an AI task request. As an example, method 900 can include the following steps.

[0427] 901. The AI-MF maintains the AI ​​capability of at least one RAN.

[0428] Step 901 may refer to the description in step 601 or step 801 and will not be repeated here.

[0429] 902. The terminal sends a task request message to the AI-MF.

[0430] The task request information is used to request the execution of the AI ​​task. In other words, it is used to request the AI-MF to determine the scheduling information for executing the AI ​​task. For the sake of distinction, the AI ​​task requested by the terminal is recorded as AI task #1.

[0431] As an example, AI task #1 may include: AI tasks related to the model, AI tasks related to the dataset, etc.

[0432] In one possible implementation, before the terminal sends the task request information to the AI-MF, the terminal establishes a connection with the AI-MF, and the terminal sends the task request information to the AI-MF based on the established connection with the AI-MF. In another possible implementation, the terminal sends the task request information to the AI-MF through another device (such as a RAN).

[0433] 903. The AI-MF determines an orchestration table for AI task #1 based on the AI ​​capability of at least one RAN.

[0434] After receiving the task request information from the terminal, the AI-MF can determine the scheduling table for AI task #1 based on the AI ​​capabilities of at least one RAN.

[0435] The orchestration table includes orchestration information of N RANs, where N is an integer greater than or equal to 1. That is, in step 903, the AI-MF determines orchestration information of N RANs for AI task #1 based on the AI ​​capabilities of at least one RAN.

[0436] Regarding the orchestration table, orchestration information, and the scheme in which the AI-MF determines the orchestration table for AI task #1 based on the AI ​​capabilities of at least one RAN, reference may be made to the relevant description in method 300 and will not be repeated here.

[0437] 904. The AI-MF sends an orchestration table or orchestration information to at least one RAN among the N RANs.

[0438] The AI-MF sends the orchestration table or orchestration information to at least one RAN among the N RANs, which may include the following implementation methods.

[0439] In a first possible implementation manner, the AI-MF sends an orchestration table to each of the N RANs.

[0440] In a second possible implementation manner, the AI-MF sends an orchestration table to one of the N RANs.

[0441] In a third possible implementation manner, the AI-MF sends the orchestration information of each RAN to each of the N RANs.

[0442] Regarding the above three implementation methods, reference may be made to the transmission method of the orchestration information of each network node in method 300, which will not be repeated here.

[0443] 905. At least one RAN among the N RANs sends response information to the AI-MF.

[0444] The response information may be used to notify the AI-MF of successful reception of the orchestration information or the orchestration table, or may be used to notify the AI-MF of whether the orchestration information or the orchestration table is approved.

[0445] In one possible implementation, if, in step 904, the AI-MF sends an orchestration table to each of the N RANs, or the AI-MF sends orchestration information of each RAN to each of the N RANs, then in step 905, the N RANs respectively send response information to the AI-MF.

[0446] In another possible implementation, if in step 904, the AI-MF sends the orchestration table to one RAN (for example, denoted as the first RAN) among the N RANs, then in step 905, the first RAN sends a response message to the AI-MF.

[0447] For the specific implementation of the response information, please refer to the relevant description in method 300, which will not be repeated here.

[0448] Method 900 is mainly described by taking the case where each RAN agrees on its own orchestration information as an example. For a solution where the RAN disagrees on the orchestration information, reference may be made to the relevant description in method 300 .

[0449] 906. The AI-MF sends a response message of the task request message to the terminal.

[0450] The response information to the task request information may be used to notify the terminal that an orchestration table has been determined for the AI ​​task #1 requested by the terminal, so that the terminal can provide an initial model or initial dataset to the RAN participating in executing AI task #1. It will be understood that if the AI-MF fails to determine the orchestration table, for example, if none of the AI ​​capabilities of at least one RAN maintained by the AI-MF in step 901 supports AI task #1, the AI-MF may also send a response information to the task request information to the terminal. This response information to the task request information is used to notify the terminal that an orchestration table cannot be provided for the AI ​​task #1 requested by the terminal.

[0451] In one possible implementation, after receiving the response to the orchestration information, the AI-MF sends a response to the task request information to the terminal. In another possible implementation, after determining the orchestration table for AI task #1, the AI-MF sends a response to the task request information to the terminal.

[0452] 907 : The terminal sends AI task #1 to N RANs.

[0453] In a possible implementation, the terminal sends AI task #1 to the first RAN among N RANs.

[0454] The first RAN indicates the first RAN among the N RANs that executes the AI ​​task #1.

[0455] For example, if AI task #1 is a model training task, the terminal sends the initial model to the first RAN among N RANs.

[0456] For another example, if AI task #1 is a dataset collection task, the terminal sends the attributes of the dataset to be collected to the first RAN among the N RANs.

[0457] 908, N RANs collaborate to perform AI task #1.

[0458] The ways to collaboratively execute AI tasks include: continuing based on the results of the AI ​​task executed by the previous RAN, or each RAN simultaneously executing the tasks for which it is responsible.

[0459] Optionally, the RAN may also schedule terminals in the cell to participate in the operation. For specific implementation, please refer to the relevant description in method 500, which will not be repeated here.

[0460] 909. The RAN sends the processing result of AI task #1 to the terminal.

[0461] The RAN in step 909 may be any one of the N RANs. For example, the RAN in step 909 may be the last RAN participating in executing AI task #1, or may be the first RAN participating in executing AI task #1, without limitation.

[0462] It is understood that the above steps are merely illustrative and are not strictly limiting. Furthermore, the sequence numbers of the above processes do not necessarily indicate the order in which they are to be executed. The order in which each process is to be executed should be determined by its function and inherent logic, and should not constitute any limitation on the implementation of the embodiments of this application.

[0463] The above describes the scenario where the control node AI-MF confirms the orchestration table for the AI ​​task by way of example in conjunction with Figure 9. Based on the above embodiment, the control node determines the operation of each network node RAN to execute the AI ​​task, which can improve overall efficiency.

[0464] It can be understood that in the above embodiment, when multiple RANs perform a certain AI task, each RAN can perform part of the AI ​​task, thereby jointly completing the AI ​​task.

[0465] It is also understood that in the above embodiment, multiple RANs sequentially executing AI tasks requested by a terminal are primarily used for illustrative purposes, and this is not intended to be limiting. For example, the AI-MF determines the tasks for each RAM, and each RAN can execute its respective tasks simultaneously or synchronously.

[0466] It is also understood that the names of some messages or information involved in the various embodiments of this application do not limit the scope of protection of the embodiments of this application. Taking A sending a message to B as an example, any message that can be used between A and B is applicable to the embodiments of this application.

[0467] It is also understood that in some of the above embodiments, sending messages is mentioned multiple times. Taking A sending a message to B as an example, A sending a message to B may include A sending the message directly to B or A sending the message to B through other devices, and there is no limitation on this.

[0468] It can also be understood that some optional features in the various embodiments of the present application may not depend on other features in certain scenarios, and may also be combined with other features in certain scenarios, without limitation.

[0469] It can also be understood that the solutions in the various embodiments of the present application can be reasonably combined and used, and the explanations or descriptions of the various terms appearing in the embodiments can be referenced or explained with each other in the various embodiments, without limitation to this.

[0470] It can also be understood that in the above-mentioned various method embodiments, the methods and operations implemented by a device (such as a terminal, a control node, or a network node) can also be implemented by components of the device (such as a chip or circuit).

[0471] Corresponding to the methods provided in the above method embodiments, embodiments of the present application also provide corresponding apparatuses, which include modules for executing the corresponding methods in the above method embodiments. The modules may be software, hardware, or a combination of software and hardware. It is understood that the technical features described in the above method embodiments are also applicable to the following apparatus embodiments.

[0472] Referring to Figure 10 , as an example, Figure 10 is a schematic block diagram of a communication device 1000 provided in an embodiment of the present application. The device 1000 includes a transceiver unit 1010 and a processing unit 1020. The transceiver unit 1010 can be used to implement corresponding communication functions. The transceiver unit 1010 can also be referred to as a communication interface or a communication unit. The processing unit 1020 can be used to implement corresponding processing functions, such as determining scheduling information or executing AI tasks.

[0473] As a design, the device 1000 is used to execute the steps or processes performed by the control node in the embodiment shown in Figure 3, and the steps or processes performed by the AI-MF in the embodiment shown in Figure 9.

[0474] In one possible implementation, the processing unit 1020 is configured to determine first orchestration information for the AI ​​task, where the first orchestration information instructs the first network node to perform the first task of the AI ​​task; and the transceiver unit 1010 is configured to send the first orchestration information to the first network node.

[0475] In one example, the processing unit 1020 is further used to determine second orchestration information for the AI ​​task, where the second orchestration information instructs the second network node to perform the second task of the AI ​​task; the transceiver unit 1010 is further used to send the second orchestration information to the first network node, or to send the second orchestration information to the second network node.

[0476] In another example, the processing unit 1020 is further used to determine second orchestration information for the AI ​​task, the second orchestration information instructing the second network node to perform the second task of the AI ​​task; the transceiver unit 1010 is further used to send the first orchestration information and the second orchestration information to the second network node; the transceiver unit 1010 is used to send the first orchestration information to the first network node, including: the transceiver unit 1010 is used to send the first orchestration information and the second orchestration information to the first network node.

[0477] In another example, the first network node is the first network node to participate in executing the AI ​​task.

[0478] In another example, the first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for executing the first task, and an exit condition for the first network node to execute the first task.

[0479] In another example, the processing unit 1020 is configured to determine first orchestration information for the AI ​​task, including: the processing unit 1020 is configured to determine the first orchestration information for the AI ​​task according to the AI ​​capability of the first network node.

[0480] In another example, the transceiver unit 1010 is further configured to receive response information from the first network node, where the response information indicates whether the first network node agrees with the first orchestration information.

[0481] As another design, the apparatus 1000 is configured to execute the steps or processes executed by the network node in the embodiment shown in FIG3 , and the steps or processes executed by the RAN in the embodiment shown in FIG9 .

[0482] In one possible implementation, the transceiver unit 1010 is configured to receive first orchestration information from a control node, where the first orchestration information instructs the first network node to perform a first task of the AI ​​task; and the processing unit 1020 is configured to execute the first task according to the first orchestration information.

[0483] In one example, the transceiver unit 1010 is used to receive first orchestration information from the control node, including: the transceiver unit 1010 is used to receive first orchestration information and second orchestration information from the control node, the second orchestration information instructing the second network node to perform the second task of the AI ​​task; the transceiver unit 1010 is also used to send the second orchestration information to the second network node.

[0484] In another example, the transceiver unit 1010 is configured to send the second orchestration information to the second network node, including: the transceiver unit 1010 is configured to send the processing result of the first task and the second orchestration information to the second network node.

[0485] In another example, the first network node is the first network node to participate in executing the AI ​​task.

[0486] In another example, the first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for executing the first task, and an exit condition for the first network node to execute the first task.

[0487] In another example, the transceiver unit 1010 is further configured to send the AI ​​capability of the first network node to the control node.

[0488] In another example, the transceiver unit 1010 is further configured to send response information to the control node, where the response information indicates whether the first network node agrees with the first orchestration information.

[0489] In another example, the transceiver unit 1010 is further used to send the first task or part of the first task to at least one terminal device; or, to send the first task or part of the first task to a second network node, where the second network node is at least one network node participating in executing the AI ​​task.

[0490] In another example, at least one terminal device is in a preset state.

[0491] In another example, the transceiver unit 1010 is further configured to send notification information to at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0492] As another design, the apparatus 1000 is configured to execute the steps or processes executed by the first network node in the embodiment shown in FIG. 4 , or the steps or processes executed by the first RAN in the embodiment shown in FIG. 6 or FIG. 8 .

[0493] In one possible implementation, the transceiver unit 1010 is configured to send a processing result and target state information of a first task of the AI ​​task to the second network node, where the target state information is used to indicate a target result of the AI ​​task.

[0494] In one example, the transceiver unit 1010 is used to send the processing result and target state information of the first task of the AI ​​task to the second network node, including: the transceiver unit 1010 is used to send the processing result and target state information of the first task of the AI ​​task to the second network node based on the AI ​​capability of the second network node.

[0495] In another example, the transceiver unit 1010 is further configured to send a first request message to the control node or the second network node, where the first request message requests the AI ​​capability of the second network node; and receive a response message to the first request message, where the response message to the first request message indicates the AI ​​capability of the second network node.

[0496] In another example, the transceiver unit 1010 is further configured to send a second request message to the second network node, where the second request message requests the second network node to collaborate in performing the AI ​​task.

[0497] In another example, the processing result of the first task represents the current status information of the AI ​​task.

[0498] In another example, the transceiver unit 1010 is further used to send area information to the second network node, and the area information is used by the second network node to determine the network node that collaborates to perform the AI ​​task.

[0499] In another example, the transceiver unit 1010 is further configured to send the first task or a portion of the first task to at least one terminal device.

[0500] In another example, at least one terminal device is in a preset state.

[0501] In another example, the transceiver unit 1010 is further configured to send notification information to at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0502] As another design, the apparatus 1000 is configured to execute the steps or processes executed by the second network node in the embodiment shown in FIG. 4 , or the steps or processes executed by the second RAN in the embodiment shown in FIG. 6 or 8 .

[0503] In one possible implementation, the transceiver unit 1010 is configured to receive a processing result and target state information of a first task of an AI task from a first network node, where the target state information is used to indicate a target result of the AI ​​task; and the processing unit 1020 is configured to execute a second task of the AI ​​task based on the processing result and target state information of the first task.

[0504] In one example, the transceiver unit 1010 is further configured to send the AI ​​capability of the second network node to the control node or the first network node.

[0505] In another example, the transceiver unit 1010 is further configured to receive a second request message from the first network node, where the second request message requests the second network node to collaborate in performing the AI ​​task.

[0506] In another example, the processing result of the first task represents the current state information of the AI ​​task; the processing unit 1020 is used to execute the second task of the AI ​​task based on the processing result of the first task and the target state information, including: the processing unit 1020 is used to execute the second task of the AI ​​task based on the current state information and the target state information of the AI ​​task.

[0507] In another example, the transceiver unit 1010 is further used to receive area information from the first network node, and the area information is used by the second network node to determine the network node that collaborates to perform the AI ​​task.

[0508] In another example, the transceiver unit 1010 is further configured to send the second task or a portion of the second task to at least one terminal device.

[0509] In another example, at least one terminal device is in a preset state.

[0510] In another example, the transceiver unit 1010 is further configured to send notification information to at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0511] As another design, the device 1000 is used to execute the steps or processes executed by the network node in the embodiment shown in Figure 5.

[0512] In one possible implementation, the transceiver unit 1010 is configured to send an AI task to at least one terminal device, wherein the at least one terminal device is in a preset state.

[0513] In another example, the transceiver unit 1010 is further configured to send notification information to at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to a preset state.

[0514] As another design, the device 1000 is used to execute the steps or processes executed by the terminal in the embodiment shown in Figure 5.

[0515] In one possible implementation, the transceiver unit 1010 is configured to receive an AI task from a network node, wherein the terminal device is in a preset state; and the processing unit 1020 is configured to execute the AI ​​task.

[0516] In another example, the transceiver unit 1010 is further configured to receive notification information from a network node, where the notification information notifies that the terminal device is adjusted to a preset state.

[0517] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0518] It should also be understood that the apparatus 1000 herein is embodied in the form of a functional unit. The term "unit" herein may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (e.g., a shared processor, a dedicated processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, combined logic circuits, and / or other suitable components that support the described functionality.

[0519] For example, the product implementation form of the apparatus 1000 provided in the embodiment of the present application is a program code that can be run on a computer.

[0520] For example, the apparatus 1000 provided in an embodiment of the present application may be a communication device, or may be a chip, a chip system (e.g., a system on chip (SoC)), or a circuit applied to a communication device. When the apparatus 1000 is a communication device, the transceiver unit 1010 may be a transceiver, or an input / output interface; the processing unit 1020 may be a processor. When the apparatus 1000 is a chip, a chip system, or a circuit used in a communication device, the transceiver unit 1010 may be an input / output interface, an interface circuit, an output circuit, an input circuit, a pin, or a related circuit on the chip, the chip system, or the circuit; the processing unit 1020 may be a processor, a processing circuit, or a logic circuit.

[0521] In addition, the transceiver unit 1010 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

[0522] Referring to Figure 11 , as an example, Figure 11 is a schematic block diagram of a communication device 1100 provided in an embodiment of the present application. The device 1100 includes a processor 1110, which is coupled to a memory 1120. Optionally, the memory 1120 is further included for storing computer programs or instructions and / or data. The processor 1110 is configured to execute the computer programs or instructions stored in the memory 1120, or read the data stored in the memory 1120, to perform the methods described in the above method embodiments.

[0523] Optionally, there are one or more processors 1110 .

[0524] Optionally, there are one or more memories 1120 .

[0525] Optionally, the memory 1120 is integrated with the processor 1110 or provided separately.

[0526] Optionally, as shown in Figure 11 , the apparatus 1100 further includes a transceiver 1130, which is configured to receive and / or transmit signals. For example, the processor 1110 is configured to control the transceiver 1130 to receive and / or transmit signals.

[0527] As a solution, the device 1100 is used to implement the operations performed by the control node in the above various method embodiments.

[0528] For example, the processor 1110 is configured to execute a computer program or instruction stored in the memory 1120 to implement the relevant operations of the control node in each of the above method embodiments, such as the method performed by the control node in the embodiment shown in FIG. 3 , or the method performed by the AI-MF in the embodiment shown in FIG. 9 .

[0529] As another solution, the device 1100 is used to implement the operations performed by the network node in the above various method embodiments.

[0530] For example, the processor 1110 is configured to execute computer programs or instructions stored in the memory 1120 to implement the relevant operations of the network node in each of the above method embodiments. For example, the method performed by the network node in the embodiment shown in FIG3 and the method performed by the RAN in the embodiment shown in FIG9 ; or the method performed by the first network node in the embodiment shown in FIG4 and the methods performed by the first RAN in the embodiments shown in FIG6 and FIG8 ; or the method performed by the second network node in the embodiment shown in FIG4 and the methods performed by the second RAN in the embodiments shown in FIG6 and FIG8 ; or the method performed by the network node in the embodiment shown in FIG5 .

[0531] As another solution, the device 1100 is used to implement the operations performed by the terminal in the above various method embodiments.

[0532] For example, the processor 1110 is configured to execute computer programs or instructions stored in the memory 1120 to implement the relevant operations of the network node in the above various method embodiments. For example, the method executed by the terminal in the embodiment shown in FIG5 .

[0533] During implementation, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 1110 or by instructions in the form of software. The method disclosed in conjunction with the embodiments of the present application can be directly embodied as being executed by a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 1120, and the processor 1110 reads the information in the memory 1120 and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0534] It should be understood that in the embodiments of the present application, the processor may be one or more integrated circuits for executing relevant programs to execute the method embodiments of the present application.

[0535] A processor (e.g., processor 1110) may include one or more processors and be implemented as a combination of computing devices. The processor may include one or more of the following: a microprocessor, a microcontroller, a digital signal processor (DSP), a digital signal processing device (DSPD), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a programmable logic device (PLD), gating logic, transistor logic, discrete hardware circuits, processing circuits, or other suitable hardware, firmware, and / or a combination of hardware and software to perform the various functions described in this disclosure. The processor may be a general-purpose processor or a special-purpose processor. For example, processor 1110 may be a baseband processor or a central processing unit. A baseband processor may be used to process communication protocols and communication data. A central processing unit may be used to enable the device to execute software programs and process data in the software programs. In addition, a portion of the processor may also include non-volatile random access memory. For example, the processor may also store information about the device type.

[0536] In this application, the term "program" is used broadly to refer to software. Non-limiting examples of software include program code, program, subroutine, instruction, instruction set, code, code segment, software module, application, or software application. The program can be executed in a processor and / or computer to cause the device to perform the various functions and / or processes described in this application.

[0537] The memory (e.g., memory 1120) can store data required by the processor (e.g., processor 1110) when executing software. The memory can be implemented using any suitable storage technology. For example, the memory can be any available storage medium that can be accessed by the processor and / or computer. Non-limiting examples of storage media include random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM), static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM), removable media, optical disk storage, magnetic disk storage media, magnetic storage devices, flash memory, registers, state memory, remotely mounted storage, local or remote memory components, or any other medium capable of carrying or storing software, data, or information and accessible by a processor / computer. It should be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0538] The memory (e.g., memory 1120) and the processor (e.g., processor 1110) may be provided separately or integrated together. The memory may be used to connect to the processor so that the processor can read information from the memory and store and / or write information in the memory. The memory may be integrated into the processor. The memory and the processor may be provided in an integrated circuit (e.g., the integrated circuit may be provided in a UE, a BS, or other network node).

[0539] 12 is a schematic block diagram of a chip system 1200 according to an embodiment of the present application. The chip system 1200 (or processing system) includes a logic circuit 1210 and an input / output interface 1220.

[0540] Logic circuit 1210 may be a processing circuit within chip system 1200. Logic circuit 1210 may be coupled to a storage unit and invoke instructions within the storage unit, enabling chip system 1200 to implement the methods and functions of various embodiments of the present application. Input / output interface 1220 may be an input / output circuit within chip system 1200, outputting information processed by chip system 1200 or inputting data or signaling information to be processed into chip system 1200 for processing.

[0541] As a solution, the chip system 1200 is used to implement the operations performed by the control node in the above various method embodiments.

[0542] For example, the logic circuit 1210 is used to implement the processing-related operations performed by the control node in the above method embodiments, such as the processing-related operations performed by the control node in the embodiment shown in Figure 3, or the processing-related operations performed by the AI-MF in the embodiment shown in Figure 9; the input / output interface 1220 is used to implement the sending and / or receiving-related operations performed by the control node in the above method embodiments, such as the sending and / or receiving-related operations performed by the control node in the embodiment shown in Figure 3, or the sending and / or receiving-related operations performed by the AI-MF in the embodiment shown in Figure 9.

[0543] As another solution, the chip system 1200 is used to implement the operations performed by the network node in the above various method embodiments.

[0544] For example, the logic circuit 1210 is used to implement the processing-related operations performed by the network node in the above method embodiments, such as the processing-related operations performed by the network node in the embodiment shown in Figure 3, or the processing-related operations performed by the RAN in the embodiment shown in Figure 9; the input / output interface 1220 is used to implement the sending and / or receiving-related operations performed by the network node in the above method embodiments, such as the sending and / or receiving-related operations performed by the network node in the embodiment shown in Figure 3, or the sending and / or receiving-related operations performed by the RAN in the embodiment shown in Figure 9.

[0545] For another example, the logic circuit 1210 is used to implement processing-related operations performed by the network nodes in the above method embodiments, such as the processing-related operations performed by the first network node and the second network node in the embodiment shown in FIG. 4 , or the processing-related operations performed by the first RAN and the second RAN in the embodiments shown in FIG. 6 and FIG. 8 ; the input / output interface 1220 is used to implement sending and / or receiving-related operations performed by the network nodes in the above method embodiments, such as the sending and / or receiving-related operations performed by the first network node and the second network node in the embodiment shown in FIG. 4 , or the sending and / or receiving-related operations performed by the first RAN and the second RAN in the embodiments shown in FIG. 6 and FIG. 8 .

[0546] As another solution, the chip system 1200 is used to implement the operations performed by the terminal in the above various method embodiments.

[0547] For example, the logic circuit 1210 is used to implement the processing-related operations performed by the terminal in the above method embodiments, such as the processing-related operations performed by the terminal in the embodiment shown in Figure 5; the input / output interface 1220 is used to implement the sending and / or receiving-related operations performed by the terminal in the above method embodiments, such as the sending and / or receiving-related operations performed by the terminal in the embodiment shown in Figure 5.

[0548] An embodiment of the present application further provides a computer-readable storage medium on which computer instructions for implementing the methods executed by the control node, network node, or terminal in the above-mentioned method embodiments are stored.

[0549] An embodiment of the present application further provides a computer program product comprising instructions, which, when executed by a computer, implement the methods performed by the control node, network node, or terminal in the above-mentioned method embodiments.

[0550] An embodiment of the present application further provides a communication system, which includes at least one of the control node, network node, and terminal in the above embodiments.

[0551] The explanation of the relevant contents and beneficial effects of any of the above-mentioned devices can be referred to the corresponding method embodiments provided above, which will not be repeated here.

[0552] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above-mentioned units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0553] The units described above as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected according to actual needs to implement the solutions provided in this application.

[0554] In addition, each functional unit in each embodiment of the present application may be integrated into one unit, each unit may exist physically separately, or two or more units may be integrated into one unit.

[0555] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0556] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. For example, the computer can be a personal computer, a server, or a network device, etc. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website, computer, server or data center to another website, computer, server or data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). About computer-readable storage media, reference can be made to the above description.

[0557] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for artificial intelligence (AI) task instruction, characterized in that: include: The control node determines first orchestration information for the AI ​​task, where the first orchestration information instructs the first network node to perform a first task of the AI ​​task; The control node sends the first orchestration information to the first network node.

2. The method according to claim 1, characterized in that The method further comprises: The control node determines second orchestration information for the AI ​​task, where the second orchestration information instructs the second network node to perform a second task of the AI ​​task; The control node sends the second orchestration information to the first network node, or the control node sends the second orchestration information to the second network node.

3. The method according to claim 1, characterized in that The method further comprises: The control node determines second orchestration information for the AI ​​task, where the second orchestration information instructs the second network node to perform a second task of the AI ​​task; The control node sends the first orchestration information and the second orchestration information to the second network node; The control node sending the first orchestration information to the first network node includes: The control node sends the first orchestration information and the second orchestration information to the first network node.

4. The method according to any one of claims 1 to 3, characterized in that The first network node is the first network node that participates in executing the AI ​​task.

5. The method according to any one of claims 1 to 4, characterized in that The first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for executing the first task, and an exit condition for the first network node to execute the first task.

6. The method according to any one of claims 1 to 5, characterized in that The control node determines first orchestration information for the AI ​​task, including: The control node determines the first orchestration information for the AI ​​task according to the AI ​​capability of the first network node.

7. The method according to any one of claims 1 to 6, characterized in that The method further comprises: The control node receives response information from the first network node, where the response information indicates whether the first network node agrees with the first orchestration information.

8. A method for artificial intelligence (AI) task instruction, characterized in that: include: A first network node receives first orchestration information from a control node, where the first orchestration information instructs the first network node to perform a first task of an AI task; The first network node performs the first task according to the first orchestration information.

9. The method according to claim 8, characterized in that The first network node receives first orchestration information from the control node, including: The first network node receives the first orchestration information and the second orchestration information from the control node, where the second orchestration information instructs the second network node to perform the second task of the AI ​​task; The method further comprises: The first network node sends the second orchestration information to the second network node.

10. The method according to claim 9, characterized in that The first network node sending the second orchestration information to the second network node includes: The first network node sends a processing result of the first task and the second orchestration information to the second network node.

11. The method according to any one of claims 8 to 10, characterized in that The first network node is the first network node that participates in executing the AI ​​task.

12. The method according to any one of claims 8 to 11, characterized in that The first orchestration information includes at least one of the following information: the first task, an identifier of the first network node, resources provided by the first network node for executing the first task, and an exit condition for the first network node to execute the first task.

13. The method according to any one of claims 8 to 12, characterized in that The method further comprises: The first network node sends the AI ​​capability of the first network node to the control node.

14. The method according to any one of claims 8 to 13, characterized in that The method further comprises: The first network node sends response information to the control node, where the response information indicates whether the first network node agrees with the first orchestration information.

15. The method according to any one of claims 8 to 14, characterized in that The method further comprises: The first network node sends the first task or a part of the first task to at least one terminal device; or The first network node sends the first task or a portion of the first task to a second network node, where the second network node is at least one network node participating in executing the AI ​​task.

16. The method according to claim 15, characterized in that The at least one terminal device is in a preset state.

17. The method according to claim 16, characterized in that Before the first network node sends the first task or a portion of the first task to at least one terminal device, the method further includes: The first network node sends notification information to the at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to the preset state.

18. A method for artificial intelligence (AI) task instruction, characterized in that: include: The first network node sends a processing result and target state information of a first AI task to the second network node, where the target state information is used to indicate a target result of the AI ​​task.

19. The method according to claim 18, characterized in that The first network node sends a processing result and target state information of a first task of the AI ​​task to the second network node, including: Based on the AI ​​capability of the second network node, the first network node sends a processing result and target state information of a first task of the AI ​​task to the second network node.

20. The method according to claim 19, wherein The method further comprises: The first network node sends first request information to the control node or the second network node, where the first request information requests the AI ​​capability of the second network node; The first network node receives response information to the first request information, where the response information to the first request information indicates the AI ​​capability of the second network node.

21. The method according to any one of claims 18 to 20, characterized in that Before the first network node sends the processing result and target state information of the first task of the AI ​​task to the second network node, the method further includes: The first network node sends second request information to the second network node, where the second request information requests the second network node to cooperate in executing the AI ​​task.

22. The method according to any one of claims 18 to 21, characterized in that The processing result of the first task represents the current status information of the AI ​​task.

23. The method according to any one of claims 18 to 22, characterized in that The method further comprises: The first network node further sends area information to the second network node, where the area information is used by the second network node to determine a network node that collaborates to execute the AI ​​task.

24. The method according to any one of claims 18 to 23, characterized in that The method further comprises: The first network node sends the first task or a part of the first task to at least one terminal device.

25. The method according to claim 24, characterized in that The at least one terminal device is in a preset state.

26. The method according to claim 25, characterized in that Before the first network node sends the first task or a portion of the first task to at least one terminal device, the method further includes: The first network node sends notification information to the at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to the preset state.

27. A method for artificial intelligence (AI) task instruction, characterized in that: include: The second network node receives a processing result and target state information of the first AI task from the first network node, where the target state information is used to indicate a target result of the AI ​​task; The second network node performs a second task of the AI ​​task based on the processing result of the first task and the target state information.

28. The method according to claim 27, characterized in that The method further comprises: The second network node sends the AI ​​capability of the second network node to the control node or the first network node.

29. The method according to claim 27 or 28, characterized in that Before the second network node receives the processing result and target state information of the first task of the AI ​​task from the first network node, the method further includes: The second network node receives second request information from the first network node, where the second request information requests the second network node to cooperate in executing the AI ​​task.

30. The method according to any one of claims 27 to 29, characterized in that The processing result of the first task represents the current status information of the AI ​​task; The second network node performs a second task of the AI ​​task based on the processing result of the first task and the target state information, including: The second network node performs a second task of the AI ​​task based on the current state information of the AI ​​task and the target state information.

31. The method according to any one of claims 27 to 30, characterized in that The method further comprises: The second network node receives the area information from the first network node, where the area information is used by the second network node to determine a network node that collaborates to execute the AI ​​task.

32. The method according to any one of claims 27 to 31, characterized in that The method further comprises: The second network node sends the second task or a part of the second task to at least one terminal device.

33. The method according to claim 32, characterized in that The at least one terminal device is in a preset state.

34. The method according to claim 33, wherein Before the second network node sends the second task or a portion of the second task to at least one terminal device, the method further includes: The second network node sends notification information to the at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to the preset state.

35. A method for artificial intelligence (AI) task instruction, characterized in that: include: A network node sends an AI task to at least one terminal device, wherein the at least one terminal device is in a preset state.

36. The method according to claim 35, characterized in that Before the network node sends the AI ​​task to at least one terminal device, the method further includes: The network node sends notification information to the at least one terminal device, where the notification information notifies that the at least one terminal device is adjusted to the preset state.

37. A method for artificial intelligence (AI) task instruction, characterized in that: include: The terminal device receives an AI task from a network node, wherein the terminal device is in a preset state; The terminal device executes the AI ​​task.

38. The method according to claim 37, wherein Before the terminal device receives the AI ​​task from the network node, the method further includes: The terminal device receives notification information from the network node, where the notification information notifies that the terminal device is adjusted to the preset state.

39. A communication device, characterized in that: include: Unit for performing the method according to any one of claims 1 to 38.

40. A communication device, characterized in that: include: a communication interface for inputting and / or outputting information; A processor, configured to execute a computer program so as to cause the apparatus to implement the method according to any one of claims 1 to 38.

41. A communication device, characterized in that include: a memory for storing executable instructions; A processor, configured to call and run the executable instructions in the memory to execute the method according to any one of claims 1 to 38.

42. The device according to any one of claims 39 to 41, characterized in that The device is any one of the following: a communication device, a chip or a chip system.

43. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program instructions, and when the program instructions are executed by a processor, the method according to any one of claims 1 to 38 is implemented.

44. A computer program product, characterized in that The computer program product comprises a computer program code, and when the computer program code is run on a computer, the method according to any one of claims 1 to 38 is implemented.

45. A communication system, characterized in that The system comprises a control node and a first network node, The control node is used to execute the method according to any one of claims 1 to 7, and the first network node is used to execute the method according to any one of claims 8 to 17.

46. ​​A communication system, characterized in that The system comprises a first network node and a second network node, The first network node is used to execute the method according to any one of claims 18 to 26, and the first network node is used to execute the method according to any one of claims 27 to 34.

Images