Communication method and communication apparatus

Abstract

The present application provides a communication method and a communication apparatus. The method comprises: a first communication apparatus acquires first information, the first information being used for indicating a transmission parameter of an air interface; on the basis of the first information and at least one of related information of a first AI task or capability information of a first node, the first communication apparatus determines first task strategy information corresponding to the first AI task and a first quality of service (QoS) requirement parameter corresponding to the first AI task, wherein the first node is a node executing the first AI task, the first task strategy information is used for indicating a task strategy of the first AI task, and the first QoS requirement parameter is a candidate QoS requirement parameter for transmission of data related to the first AI task over the air interface; and the first communication apparatus sends second information, the second information being used for indicating the first QoS requirement parameter. The communication efficiency and the QoS of a system can be improved.

Description

Communication method and communication apparatus

[0001] The present application claims priority to the Chinese patent application No. 202411394435.9, filed on September 30, 2024, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communications, and more particularly, to a communication method and a communication apparatus. BACKGROUND

[0003] In recent years, artificial intelligence (AI) technology has made a leap, and the deep integration of AI technology and communication technology has become one of the important visions of future communication systems. On the one hand, AI models can replace traditional communication modules to achieve more intelligent network functions, such as AI models can be applied to beam management, channel prediction, resource allocation, etc. in the physical layer, and load balancing, energy saving, etc. in higher protocol layers. On the other hand, the computing, transmission capabilities and perceived information in the network can also support third-party AI applications of mobile terminals, such as the computing of third-party AI applications can be offloaded to computing nodes in the network, or the environmental information perceived by the network can provide better personalized services. As can be seen, AI services as a major feature of new capabilities of communication networks is the integration of communication and computing.

[0004] However, how to support the integration of communication and computing in the communication system is a problem to be solved at present. SUMMARY

[0005] Embodiments of the present application provide a communication method and a communication apparatus, which can improve communication efficiency and system service quality.

[0006] In a first aspect, a communication method is provided, which can be performed by a first communication apparatus. The first communication apparatus can be a network device or a unit / module / component (such as a chip, a chip system, a logic circuit, or software) configurable to (or usable for) the network device. Hereinafter, the method performed by the first communication apparatus is taken as an example for description.

[0007] The method comprises: a first communication device obtaining first information, the first information being used to indicate a transmission parameter of an air interface. The first communication device determines, according to the first information and at least one of related information of a first artificial intelligence (AI) task or capability information of a first node, first task policy information corresponding to the first AI task and a first quality of service (QoS) requirement parameter corresponding to the first AI task, wherein the first node is a node performing the first AI task, the first task policy information is used to indicate a task policy of the first AI task, and the first QoS requirement parameter is a candidate QoS requirement parameter for the air interface to transmit data related to the first AI task. The first communication device sends second information, the second information being used to indicate the first QoS requirement parameter.

[0008] To effectively support the integration of communication and computing in a communication system, embodiments of the present application propose that a first communication device can perform joint optimization of communication and computing based on a transmission parameter of a communication-related air interface and at least one of AI task-related information or capability information of a node performing the task, so as to balance the efficiency and quality of communication and computing, obtain AI task policy information and communication QoS requirement parameters closer to the optimal solution, and apply the optimized AI task policy information and QoS parameter information, thereby improving the efficiency and quality of communication and computing. Further, the result obtained by executing the AI task can be applied to a communication service and / or a third-party application, thereby improving the communication efficiency of the communication system and the service quality of the system.

[0009] In some implementations, the transmission parameter comprises a transmission state parameter and / or a transmission capability parameter of the air interface.

[0010] According to the above scheme, the transmission parameter of the air interface can include related parameters when the air interface is in a transmission state, and / or can include related parameters of transmission capability that can be provided for the first AI task, so that the first communication device can take the communication-related transmission state and / or transmission capability as a constraint term to solve the joint optimization problem of communication and computing, and can balance the efficiency and quality of communication and computing to obtain AI task policy information and communication QoS requirement parameters close to the optimal solution.

[0011] Exemplarily, the transmission state parameter comprises one or more of the following transmission state parameters of the air interface transmitting data related to the first AI task:

[0012] a transmission rate, a transmission delay, a packet loss rate, a predicted value of the transmission rate, a predicted value of the transmission delay, or a predicted value of the packet loss rate.

[0013] When the air interface is transmitting or has transmitted data related to the first AI task, the transmission state parameter can include a transmission state parameter of the air interface transmitting data related to the first AI task, and / or a predicted value of the transmission state parameter based on the current transmission state.

[0014] Exemplarily, the transmission capability parameter includes one or more of the following transmission parameters supported by the air interface:

[0015] a maximum transmission rate supported, a minimum transmission latency supported, or a minimum packet loss rate.

[0016] In some implementations, the capability information of the first node includes at least one of a computing capability or progress information of a currently running task.

[0017] According to the above scheme, when the first communication device performs communication and computing joint optimization, the computing capability of the node performing the first AI task and / or the progress of the current task can be referred to, so as to balance the efficiency and quality of communication and computing, and obtain a better optimization result.

[0018] In some implementations, the first task strategy information is used to indicate one or more of the following task strategies: a task execution manner, a task requirement, a computing queue priority, or a resource allocation manner.

[0019] The task strategy information can include a task execution manner. For example, the task execution manner can be that the first AI task is executed by at least one of a terminal side, a network side, or a cloud server side.

[0020] The task strategy information can include a task requirement. For example, the task requirement can include at least one of an accuracy requirement and a latency requirement, and exemplarily, the task requirement can be at least one of an accuracy requirement of an expected inference result of a model, an inference latency requirement, a model selection requirement, and an inference task allocation requirement, based on different types of tasks.

[0021] The task strategy information can include a computing queue priority. For example, the first AI task can include multiple subtasks or multiple computing processes, and the computing queue priority includes a priority of executing each subtask and / or a priority of executing each computing process.

[0022] The task strategy information can include a resource allocation manner. The resource allocation manner can include, but is not limited to, an allocation manner of computing resources and / or storage resources of a node executing the AI task, etc.

[0023] According to the above scheme, through joint optimization of communication and computing, a task strategy balancing the efficiency and quality of communication and computing can be obtained, so that after the task strategy is applied, the communication efficiency and service quality can be improved.

[0024] In some embodiments, the first information is further used to indicate a second QoS requirement parameter, the second QoS requirement parameter being a QoS requirement parameter corresponding to the data related to the first AI task currently.

[0025] According to the above scheme, the first communication device performing joint optimization can also refer to the QoS requirement parameter currently applied in communication, so as to obtain a better optimization result.

[0026] In some embodiments, the related information of the first AI task includes one or more of the following: current execution progress information, current task policy information, or initial configuration information of the task.

[0027] According to the above scheme, when the first communication device performs joint optimization of communication and calculation, it can refer to at least one of the related information of the first AI task, such as the current execution progress, the current task policy, or the initial configuration of the task, and combine the current situation of the first AI task, to balance the efficiency and quality of communication and calculation, and obtain a better optimization result.

[0028] In some embodiments, the method further includes: determining, by the first communication device, configuration information of the first AI task according to the first task policy information. The first communication device sends the configuration information to the first node.

[0029] According to the above scheme, the first communication device can be a node configured to perform AI tasks, for example, the first communication device can be a service unit SU, therefore, after obtaining the optimization result, the first communication device can determine the task configuration information based on the first task policy information obtained by optimization, and apply the task policy indicated by the first task policy information, and configure (or reconfigure) the first AI task through the task configuration information for the node performing the first AI task, that is, the subtask (or calculation process) and execution requirement, mode, etc. responsible for by each node.

[0030] In some embodiments, the first communication device determining the first task policy information and the first QoS requirement parameter includes: the first communication device determining at least one task policy information and a plurality of candidate QoS requirement parameters, the at least one task policy information including the first task policy information, and the plurality of candidate QoS requirement parameters including the first QoS requirement parameter, wherein the second information is used to indicate the plurality of candidate QoS requirement parameters.

[0031] According to the above scheme, the first communication device can determine a plurality of candidate QoS requirement parameters, so that the second communication device can determine a more suitable QoS requirement parameter based on the actual situation of the access network and the air interface. Further improve the performance of joint optimization of communication and calculation. For example, the first communication device can be a SU, and the second communication device can be a CU.

[0032] In some implementations, the at least one task policy information is the first task policy information, and the first task policy information indicates that a task policy supported by the first task policy information supports the plurality of candidate QoS requirement parameters.

[0033] In some implementations, the at least one task policy information includes a plurality of task policy information corresponding to the plurality of candidate QoS requirement parameters, and the method further includes: the first communication device receiving third information used to indicate the first QoS requirement parameter in the plurality of candidate QoS requirement parameters, the first QoS requirement parameter being a QoS requirement parameter of the air interface application. The first communication device determines the first task policy information according to the first QoS requirement parameter, the first task policy information being task policy information corresponding to the first QoS requirement parameter in the plurality of task policy information.

[0034] In some implementations, before the first communication device obtains the first information, the method further includes: the first communication device receiving fourth information used to indicate that the air interface cannot meet the updated QoS requirement parameter.

[0035] According to the above scheme, the first communication device can receive the fourth information, determine that the air interface cannot meet the updated QoS requirement parameter according to the fourth information, and trigger the reconfiguration of the first AI task through the fourth information. After the first AI task is reconfigured, the first communication device can obtain the first information, and perform joint optimization of communication and calculation according to the first information, and according to the related information of the first AI task (i.e. the related information of the first AI task obtained after reconfiguration) or the capability information of the first node, to obtain an optimization result, i.e. the first task policy information and the first QoS requirement parameter. The situation that the data transmission quality related to the first AI task is reduced due to the fact that the air interface cannot meet the updated QoS requirement parameter can be avoided, and the system reliability is improved.

[0036] In some implementations, the method further includes: the first communication device receiving fifth information including the related information of the first AI task and / or the capability information of the first node. The first communication device sends the first task policy information.

[0037] According to the above scheme, the first communication device can obtain the related information of the first AI task and / or the capability information of the first node through the fifth information, so as to refer to the information indicated by the fifth information to implement the joint optimization of communication and calculation.

[0038] In a second aspect, a communication method is provided, which can be performed by a second communication device, which can be a network device or a unit / module / component (e.g., or a chip, or a chip system, or a logic circuit, or software) configurable to (or usable for) a network device. The following is described by way of example with the second communication device performing the method.

[0039] The method comprises: sending, by the second communication device, first information, the first information being used to indicate a transmission parameter of an air interface. Receiving, by the second communication device, second information, the second information being used to indicate a first QoS requirement parameter, the first QoS requirement parameter being a QoS requirement parameter of the air interface for transmitting data related to a first AI task, the first QoS requirement parameter being obtained according to at least one of the first information and related information of the first AI task or capability information of the first node.

[0040] It should be noted that the definitions of the information and the parameters in the second aspect can refer to the descriptions in the first aspect, which will not be repeated here for brevity.

[0041] In some implementations, the first information is further used to indicate a second QoS requirement parameter, the second QoS requirement parameter being a QoS requirement parameter corresponding to the data related to the first AI task.

[0042] In some implementations, the method further comprises: sending, by the second communication device, sixth information to an access and mobility management function node, the sixth information being used to indicate the first QoS requirement parameter, the first QoS requirement parameter being an updated QoS requirement parameter applied by the air interface.

[0043] The second communication device can notify the access and mobility management function node that the updated QoS requirement parameter is the first QoS requirement parameter, i.e., the QoS requirement parameter obtained through the communication and joint optimization process is the first QoS requirement parameter, through the sixth information. The access and mobility management function node can notify the terminal of the updated QoS requirement parameter through the session management function node. It should be noted that in specific implementations, a node having a similar function can also implement the function of the access and mobility management function node. That is, the second communication device can send the sixth information to enable the updated QoS requirement parameter to be delivered to the terminal.

[0044] In a third aspect, a communication method is provided, which can be performed by a second communication device, which can be a network device or a unit / module / component (e.g., or a chip, or a chip system, or a logic circuit, or software) configurable to (or usable for) a network device. The following is described by way of example with the second communication device performing the method.

[0045] The method further includes: the second communication device sending fifth information, the fifth information including related information of the first AI task and / or capability information of the first node, the first node being a node providing an AI service. The second communication device receives first task policy information, the first task policy information being used to indicate a task policy of the first AI task, the first task policy being obtained according to a transmission parameter of an air interface and the fifth information.

[0046] It should be noted that the definitions of the information and the parameters in the third aspect can refer to the descriptions in the first aspect, which will not be repeated here for brevity.

[0047] In some implementations, the method further includes: the second communication device determining configuration information of the first AI task according to the first task policy information. The second communication device sends the configuration information to the first node.

[0048] In a fourth aspect, a communication device is provided. In one design, the device can include a module corresponding to each of the methods / operations / steps / actions described in the first aspect or any of the implementations of the first aspect. The module can be implemented in hardware circuitry, software, or a combination of hardware circuitry and software. In one design, the device includes a processing unit configured to obtain first information, the first information being used to indicate a transmission parameter of an air interface. The processing unit is further configured to determine, according to the first information and according to at least one of related information of a first artificial intelligence (AI) task or capability information of a first node, first task policy information corresponding to the first AI task and first quality of service (QoS) requirement parameters corresponding to the first AI task, wherein the first node is a node executing the first AI task, the first task policy information is used to indicate a task policy of the first AI task, and the first QoS requirement parameters are candidate QoS requirement parameters for the air interface to transmit data related to the first AI task. The device further includes a transceiver configured to send second information, the second information being used to indicate the first QoS requirement parameters.

[0049] It should be noted that the definitions of the information and the parameters in the fourth aspect can refer to the descriptions in the first aspect, which will not be repeated here for brevity.

[0050] In some implementations, the processing unit is further configured to determine configuration information of the first AI task according to the first task policy information. The transceiver is further configured to send the configuration information to the first node.

[0051] In some embodiments, the processing unit is specifically configured to determine at least one task policy information and a plurality of candidate QoS requirement parameters, the at least one task policy information comprises the first task policy information, and the plurality of candidate QoS requirement parameters comprises the first QoS requirement parameter, wherein the second information is used to indicate the plurality of candidate QoS requirement parameters.

[0052] In some embodiments, the at least one task policy information comprises a plurality of task policy information, the plurality of task policy information corresponds to the plurality of candidate QoS requirement parameters, the transceiver is further configured to receive third information, the third information is used to indicate the first QoS requirement parameter in the plurality of candidate QoS requirement parameters, and the first QoS requirement parameter is a QoS requirement parameter of the air interface application; and the processing unit is further configured to determine the first task policy information according to the first QoS requirement parameter, and the first task policy information is a task policy information corresponding to the first QoS requirement parameter in the plurality of task policy information.

[0053] In some embodiments, before the processing unit obtains the first information, the transceiver is further configured to receive fourth information, the fourth information is used to indicate that the air interface cannot meet the updated QoS requirement parameter.

[0054] In some embodiments, the transceiver is further configured to receive fifth information, the fifth information comprises related information of the first AI task and / or capability information of the first node. The transceiver is further configured to send the first task policy information.

[0055] In a fifth aspect, a communication apparatus is provided. In one design, the apparatus can include a module corresponding to each of the methods / applications / steps / actions described in the second aspect or any of the implementations of the second aspect. The module can be hardware circuitry, software, or a combination of hardware circuitry and software. In one design, the apparatus includes a processing unit configured to determine first information, the first information being used to indicate a transmission parameter of an air interface. The apparatus includes a transceiver configured to send the first information. The transceiver is further configured to receive second information, the second information being used to indicate a first QoS requirement parameter, the first QoS requirement parameter being a QoS requirement parameter of the air interface for transmitting data related to a first AI task, and the first QoS requirement parameter being determined according to the first information and at least one of related information of the first AI task or capability information of the first node.

[0056] It is noted that the definitions of the information and parameters in the fifth aspect can be referred to the descriptions in the first aspect, which will not be repeated here for brevity.

[0057] In some embodiments, the transceiver is further configured to send, to the AMF node, sixth information indicating the first QoS requirement parameter, the first QoS requirement parameter being an updated QoS requirement parameter of the air interface application.

[0058] In a sixth aspect, a communication apparatus is provided. In one design, the apparatus can include a module corresponding to each of the methods / applications / steps / actions described in the second aspect or any of the implementations of the second aspect. The module can be implemented in hardware circuitry, software, or both. In one design, the apparatus includes a processing unit configured to determine fifth information including related information of a first AI task and / or capability information of a first node, the first node being a node providing an AI service. The apparatus includes a transceiver configured to send the fifth information. The transceiver is further configured to receive first task policy information indicating a task policy of the first AI task, the first task policy being derived based on a transmission parameter of an air interface and the fifth information.

[0059] In some embodiments, the processing unit is further configured to determine configuration information of the first AI task based on the first task policy information. The transceiver is further configured to send the configuration information to the first node.

[0060] In a seventh aspect, a communication apparatus is provided. The communication apparatus includes a processor. The processor can implement the methods in the first aspect to the third aspect and any of the possible implementations of the first aspect to the third aspect. Optionally, the communication apparatus further includes a memory, and the processor is coupled to the memory and configured to execute instructions stored in the memory to implement the methods in the first aspect to the third aspect and any of the possible implementations of the first aspect to the third aspect. Optionally, the communication apparatus further includes a communication interface, and the processor is coupled to the communication interface. In embodiments of the present disclosure, the communication interface can be a transceiver, a pin, a circuit, a bus, a module, or any other type of communication interface, which is not limited.

[0061] In one implementation, the communication apparatus is a communication device (e.g., an access network device or a core network device). When the communication apparatus is a communication device, the communication interface can be a transceiver, or an input / output interface.

[0062] In another implementation, the communication apparatus is a chip configured in a communication device. When the communication apparatus is a chip configured in a communication device, the communication interface can be an input / output interface.

[0063] Optionally, the transceiver can be a transceiver circuit. Optionally, the input / output interface can be an input / output circuit.

[0064] In an eighth aspect, a processor is provided, including: an input circuit, an output circuit, and a processing circuit. The processing circuit is configured to receive a signal through the input circuit and transmit a signal through the output circuit, so that the processor performs the method in the first aspect to the third aspect and any possible implementation manner of the first aspect to the third aspect.

[0065] In a specific implementation process, the processor can be one or more chips, the input circuit can be an input pin, the output circuit can be an output pin, and the processing circuit can be a transistor, a gate circuit, a flip-flop, and various logic circuits, etc. The input signal received by the input circuit can be received and input by, for example but not limited to, a receiver, the signal output by the output circuit can be output to and transmitted by, for example but not limited to, a transmitter, and the input circuit and the output circuit can be the same circuit which is used as the input circuit and the output circuit at different times. The embodiments of the present application do not limit the specific implementation manner of the processor and various circuits.

[0066] In a ninth aspect, a computer program product is provided, including: a computer program (also referred to as code or instructions), which, when executed, causes a computer to perform the method in the first aspect to the third aspect and any possible implementation manner of the first aspect to the third aspect.

[0067] In a tenth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code or instructions), which, when executed on a computer, causes the computer to perform the method in the first aspect to the third aspect and any possible implementation manner of the first aspect to the third aspect.

[0068] In an eleventh aspect, a communication system is provided, including at least one first communication device and at least one second communication device.

[0069] It should be understood that the beneficial effects of the features corresponding to the first aspect in the second aspect to the eleventh aspect can be referred to the related description of the first aspect, which will not be described here again. BRIEF DESCRIPTION OF DRAWINGS

[0070] FIG. 1 is a schematic diagram of a communication system architecture suitable for embodiments of the present application;

[0071] FIG. 2 is a schematic diagram of a structure of an access network provided by embodiments of the present application;

[0072] FIG. 3 is another schematic diagram of a structure of an access network provided by embodiments of the present application;

[0073] FIG. 4 is another schematic diagram of a communication system architecture suitable for embodiments of the present application;

[0074] FIG. 5 is a schematic flow chart of a communication method according to an embodiment of the present application;

[0075] FIGS. 6 to 8 are other different schematic flow charts of a communication method according to an embodiment of the present application;

[0076] FIG. 9 is a schematic block diagram of an example of a communication device according to an embodiment of the present application;

[0077] FIG. 10 is a schematic structural diagram of another example of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0078] For the convenience of understanding the embodiments of the present application, the following explanations are first made:

[0079] In the present application, "indication" can include direct indication, indirect indication, display indication, and implicit indication. When describing that 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.

[0080] In the present application, " / " can represent that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" can be used to describe the existence of three relationships of associated objects, for example, A and / or B, which can represent three cases of A existing alone, A and B existing together, and B existing alone, where A and B can be singular or plural.

[0081] In the present application, "at least one" means one or more, and "multiple" means two or more, such as three, four, or more. Similar expressions (such as at least one, at least one, etc.) are the same. "At least one of the following", "one or more of the following" or the like means any combination of these items, which can include only a single item or a combination of multiple items. For example, at least one of a, b, or c can represent: a, or b, or c; a and b; or, a and c; or, b and c; or, a and b and c. Where a, b, and c can be single or multiple.

[0082] In the present application, in order to facilitate the description of the technical solutions of the embodiments of the present application, "first", "second", etc. can be used for distinction in the embodiments of the present application. The "first", "second", etc. do not limit the quantity and execution order, and the "first", "second", etc. do not necessarily mean different.

[0083] In this application, the words "exemplary," "example," or "e.g." are used to mean example, by way of illustration or demonstration, and should not be construed as meaning "preferred" or "advantageous" over other embodiments or designs. The use of "exemplary," "example," or "e.g." is intended to present the relevant concept in a concrete manner, facilitating understanding.

[0084] In this application, "sending information / data" only represents the direction of information / data transmission, including direct sending by the communication interface (such as air interface (short for air interface)) of the device, "sending" can also be understood as the "output" of the module interface, and "sending" can include indirect sending by the processing unit through the communication interface, that is, the processing unit outputs information / data through the module interface, and then transmits to the communication interface of the device for sending. "Receiving information / data" only represents the direction of information / data transmission, including direct receiving by the communication interface, "receiving" can also be understood as the "input" of the module interface, and "receiving information / data" can include indirect receiving by the processing unit through the communication interface, that is, the communication interface receives information / data, and then transmits to the module interface of the processing unit, and the module interface inputs the information / data to the processing unit. "Sending information / data to (such as terminal)" can be understood as that the destination of the information is the terminal. It can include direct or indirect sending of information / data to the terminal. "Receiving information / data from (such as terminal)" can be understood as that the source of the information is the terminal. It can include direct or indirect receiving of information / data from the terminal. The information / data between the source and the destination of the information / data transmission can be processed as necessary, such as format change, etc., but the destination can understand the valid information / data from the source. Similar expressions in this application can be understood similarly, and will not be repeated here.

[0085] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as long term evolution (LTE) system, 5th generation (5G) communication system, satellite communication system, wireless fidelity (WiFi) system, and the solutions provided by the present application can also be applied to future communication systems or other communication systems, etc. The present application does not make any limitation in this regard.

[0086] Figure 1 shows a possible, non-limiting, schematic representation of a system. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100, a core network (CN) 200, and a data network (DN) 300. The RAN 100 includes at least one RAN node (e.g., 110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (e.g., 120a-120j in Figure 1, collectively referred to as 120). Other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1), etc., can also be included in the RAN 100. The terminals 120 are wirelessly connected to the RAN nodes 110. The access network nodes (or RAN nodes) 110 are connected to the core network 200 through wireless or wired means. The core network devices in the core network 200 and the access network nodes 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device that integrates the core network logical functions and the radio access network logical functions.

[0087] The RAN 100 can be a 3rd generation partnership project (3GPP) related cellular system, e.g., a 4G, 5G mobile communication system, or a future evolution system. The RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system that integrates two or more of the above systems.

[0088] The access network nodes 110, which can also be referred to as access network devices, RAN entities, or access nodes, etc., form part of the communication system to help terminals to access wirelessly. The multiple access network nodes 110 in the communication system 10 can be nodes of the same type or nodes of different types. In some scenarios, the roles of the access network nodes 110 and the terminals 120 are relative, e.g., the network element 120i in Figure 1 can be a helicopter or a drone, which can be configured as a mobile base station. For a terminal 120j that accesses the RAN 100 through the network element 120i, the network element 120i is a base station; but for the base station 110a, the network element 120i is a terminal. The access network nodes 110 and the terminals 120 are sometimes referred to as communication apparatuses, e.g., the network elements 110a and 110b in Figure 1 can be understood as communication apparatuses with base station functions, and the network elements 120a-120j can be understood as communication apparatuses with terminal functions.

[0089] In a possible scenario, the access network node can be a base station, such as an evolved NodeB (eNodeB), a next generation NodeB (gNB), or a base station in a future mobile communication system. The access network node can be a macro base station (such as 110a in FIG. 1), a micro base station or an indoor station (such as 110b in FIG. 1), a relay node or a donor node, or a wireless controller in a CRAN scenario. Alternatively, the access network node can be an access point (AP), a transmission reception point (TRP), an access node in a WiFi system, or the like. Optionally, the access network node can also be a server, a wearable device, a vehicle or a vehicle-mounted device, and the like. For example, the access network device in vehicle to everything (V2X) technology can be a road side unit (RSU). All or part of the functions of the access network node in this application can also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (such as a cloud platform). The access network node in this application can also be a logical node, a logical module or software that can implement all or part of the functions of the access network node.

[0090] In another possible scenario, multiple access network nodes cooperate to assist a terminal to implement wireless access, and different access network nodes respectively implement part of the functions of a base station.

[0091] For example, the access network node can be a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), and the like as shown in FIG. 2. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a radio frequency remote unit (RRU), an active antenna processing unit (AAU), or a remote radio head (RRH).

[0092] The CU and the DU can implement part of the protocol layer functions of the access network device respectively. For example, the CU can be responsible for processing non-real-time protocols and services. The DU can be responsible for processing physical (PHY) layer protocols and real-time services. One DU can be connected to only one CU or connected to multiple CUs, and one CU can be connected to multiple DUs. The CU and the DU can communicate with each other through an F1 interface. The CU can further include a CU-CP and a CU-UP. The CU-CP can be responsible for control plane functions, and the CU-UP can be responsible for user plane functions. The CU-CP and the CU-UP can communicate with each other through an E1 interface. The CU-CP can communicate with the core network through an NG interface on behalf of the access network device, and communicate with the DU through an F1-C interface. The CU-UP can communicate with the DU through an F1-U interface, but the present application is not limited thereto.

[0093] In different systems, the CU (or CU-CP and CU-UP), DU, or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an open-CU (O-CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, any of the CU (or CU-CP, CU-UP), DU, and RU can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0094] For another example, the access network node can be a CU, a DU, an RU, or a service unit (SU) as shown in FIG. 3. The SU is an access network node for providing AI application services. The SU and the CU can be separately arranged, or the SU can belong to a part of the CU. The CU and the DU can be separately arranged, or can be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as an RRU, an AAU, or an RRH.

[0095] The terminal can also be referred to as a terminal device, a user equipment (UE), a mobile station, a mobile terminal, etc. The terminal can be widely applied to various scenarios for communication. The scenarios include, for example, but are not limited to, at least one of the following: enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), massive machine-type communications (mMTC), D2D, V2X, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, automatic driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, sensing terminal, terminal integrated with communication and sensing, or smart city, etc. The terminal can be a mobile phone (such as 120a, 120j and 120e in FIG. 1), a tablet computer, a computer with wireless transceiver function (such as 120g in FIG. 1), a customer-premises equipment (CPE), a smart point of sale (POS) machine, a light UE, a reduced capability UE (REDCAP UE), a wearable device, a vehicle (such as 120b in FIG. 1), a drone, a helicopter, an airplane (such as 120i in FIG. 1), a ship, a robot, a mechanical arm, a sensor, a perceiver, or a smart home device (such as 120h in FIG. 1), etc.

[0096] FIG. 4 shows another possible, non-limiting system. The system architecture includes a user equipment (UE), a RAN node, and a core network node, which can include, for example, a policy control function (PCF) node, an access and mobility management function (AMF) node, a session management function (SMF) node, a UPF node, and an application function (AF) node, as shown in FIG. 4.

[0097] The functions of each core network node are introduced below. Among them, the AUSF node is mainly responsible for authenticating the user to determine whether to allow the user or device to access the network. The AMF node mainly performs mobility management, access authentication / authorization, etc. In addition, the AMF node is also responsible for transmitting user policies between the UE and the PCF node. The SMF node is mainly responsible for completing the IP address allocation of the UE. The UPF node is mainly responsible for selecting, charging, and QoS policy control, etc. Session management functions. The UPF node serves as an interface with the data network (DN) and is mainly responsible for completing user plane data forwarding, session / stream-based charging statistics, bandwidth limitation, etc. The AF node mainly transmits application layer requirements for the network side. The PCF node is mainly responsible for policy management of charging policies and QoS policies.

[0098] As shown in FIG. 4, the functional units can communicate with each other through next generation (NG) interfaces. For example, the UE can transmit control plane messages to the AMF node through an NG interface 1 (N1), the RAN node can establish a user plane data transmission channel with the UPF through an NG interface 3 (N3), the RAN node can establish a control plane signaling connection with the AMF node through an NG interface 2 (N2), the UPF can exchange information with the SMF node through an NG interface 4 (N4), the UPF can exchange user plane data with the data network DN through an NG interface 6 (N6), the AMF node can exchange information with the SMF node through an NG interface 11 (N11), and the SMF node can exchange information with the PCF node through an NG interface 7 (N7). It should be noted that FIG. 4 is only an exemplary architecture diagram, and the network architecture can include other functional nodes in addition to the functional nodes shown in FIG. 4.

[0099] The system architecture can also include a server (which can be referred to as a cloud server). The server can provide computing or application services for devices that require complete integrity transmission services, including control servers and application servers, etc.

[0100] In order to effectively support communication and computing convergence in a communication system, embodiments of the present application propose that the access network node can jointly optimize communication and computing globally, trade off the efficiency and quality of communication and computing, obtain an AI task policy and communication QoS requirement parameter closer to the optimal solution, improve the efficiency and quality of communication and computing, and apply the result of executing the AI task to communication services and / or third-party applications, thereby improving the communication efficiency of the communication system and the service quality of the system.

[0101] The technical solutions in the present application will be described below with reference to the drawings.

[0102] FIG. 5 is a schematic flow chart of a communication method 500 provided by an embodiment of the present application. The communication method can be performed by a first communication device, which can be an access network device in an access network, or a unit / module / component (such as a software module, a chip, a logic circuit) configurable to (usable to) implement the functions of the access network device, or an access network node in the access network, for example, the first communication device can be a base station, a CU or a SU.

[0103] The communication method 500 can include, but is not limited to, the following S501 to S503.

[0104] S501, the first communication device obtains first information, the first information being used to indicate a transmission parameter of an air interface.

[0105] For example, the first communication device can be an access network device, and the first communication device obtaining the first information can include: the access network device determining the first information, the air interface being an interface between the access network device and a terminal, and the access network device determining the transmission parameter of the air interface according to monitoring of the air interface.

[0106] For another example, the first communication device can be a CU, and the first communication device obtaining the first information can include: the CU receiving the first information, such as the first information being from a DU, and the CU determining the transmission parameter of the air interface between the access network node and the terminal according to the first information.

[0107] For yet another example, the first communication device can be a SU, and the first communication device obtaining the first information can include: the SU receiving the first information, such as the SU receiving the first information from the CU or from the DU, and determining the transmission parameter of the air interface between the access network node and the terminal according to the first information.

[0108] Optionally, the transmission parameter of the air interface can include a transmission capability parameter and / or a transmission state parameter.

[0109] The transmission parameter of the air interface can include the transmission capability parameter, and the transmission capability parameter can be a transmission capability parameter that the air interface is capable of providing for transmission of data related to the first AI task.

[0110] For example, the transmission capability parameter can include one or more of the following transmission parameters of the air interface: a maximum transmission rate supported, a minimum transmission delay supported, or a minimum packet loss rate.

[0111] When the air interface is transmitting or has transmitted the data related to the first AI task, the transmission parameter can include a transmission state parameter of the air interface transmitting the data related to the first AI task, the transmission state parameter can include a transmission state parameter when the data related to the first AI task is transmitted, and / or a predicted value of the transmission state parameter. The predicted value of the transmission state parameter can be determined based on the transmission state parameter when the data related to the first AI task is transmitted.

[0112] For example, the transmission state parameter can include, but is not limited to, one or more of the following transmission state parameters: transmission rate, transmission delay, packet loss rate, predicted value of the transmission rate, predicted value of the transmission delay, or predicted value of the packet loss rate.

[0113] Optionally, the first information is further used to indicate a second QoS requirement parameter, and the second QoS requirement parameter is a QoS requirement parameter corresponding to the data related to the first AI task.

[0114] That is, the second QoS requirement parameter is a QoS requirement parameter that needs to be met when the air interface transmits the data related to the first AI task.

[0115] For example, in this application, the QoS requirement parameter can include, but is not limited to, one or more of the following parameters: 5G QoS indicator (5G QoS Indicator, 5QI), allocation and retention priority (allocation and retention priority, ARP), guaranteed flow bit rate (guaranteed flow bit rate, GFBR), non-guaranteed flow bit rate (non-guaranteed flow bit rate, Non-GFBR), maximum flow bit rate (maximum flow bit rate, MFBR) or aggregated maximum bit rate (aggregated maximum bit rate, AMBR), QoS class identifier (QoS class identifier, QCI).

[0116] S502, the first communication device determines first task policy information corresponding to the first AI task and first quality of service (quality of service, QoS) requirement parameters corresponding to the first AI task according to the first information and at least one of the related information of the first AI task or the capability information of the first node, the first node is a node executing the first AI task, the first task policy information is used to indicate the task policy of the first AI task, and the first QoS requirement parameter is a candidate QoS requirement parameter of the air interface transmitting the data related to the first AI task.

[0117] The first communication device can perform joint optimization of communication and computation according to the transmission parameters of the air interface, in combination with at least one of the first AI task-related information or the capability information of the first node, and can obtain the results of the respective optimization of communication and computation, i.e., the first QoS requirement parameter is the corresponding communication-related optimized QoS requirement parameter of the first AI task, and the first task policy information is the corresponding computation-related optimized task policy information of the first AI task. Optionally, when the first information further indicates the second QoS requirement parameter, the first communication device further refers to the second QoS requirement parameter when performing the joint optimization of communication and computation.

[0118] If the first communication device needs to perform joint optimization of communication and computation according to the first AI task-related information, the first communication device can obtain the first AI task-related information.

[0119] For example, the first communication device can be a node providing an AI service. If the first communication device is an SU, the SU can determine the first AI task-related information based on its own monitoring of the first AI task, e.g., the SU can obtain part or all of the first AI task-related information from a node executing the first task, and / or part or all of the first AI task-related information can be generated by the SU.

[0120] For another example, the first communication device can be a CU, which can receive the first AI task-related information from an SU.

[0121] Exemplarily, the first AI task-related information can include but is not limited to one or more of the following: current execution progress information, current task policy information, or initial configuration information of the task.

[0122] If the first AI task has been started, the first AI task-related information can include current execution progress information of the first AI task. Exemplarily, the current execution progress information can indicate the completion of the first AI task, e.g., the completion can include but is not limited to one or more of the following: the proportion of the completed part in the total task, the proportion of the uncompleted part in the total task, the execution time, or the remaining execution time.

[0123] Exemplarily, in the embodiments of the present application, the task policy information can be used to indicate one or more of the following task policies: task execution mode, task requirement, computation queue priority, or resource allocation mode.

[0124] The first AI task-related information can include current task policy information.

[0125] The task policy information can indicate a task execution manner. The current task policy information in the related information of the first AI task can indicate a task execution manner currently adopted by the first AI task. The task execution manner can be that at least one side device of a terminal side, a network side, or a cloud server side executes the first AI task. For example, the terminal side can execute the first AI task alone, or the network side can execute the first AI task. Alternatively, the terminal side and the network side can cooperate to execute the first AI task, or the terminal side and the cloud server side can cooperate to execute the first AI task, or the network side and the cloud server side can cooperate to execute the first AI task. Alternatively, the terminal side, the network side, and the cloud server side can cooperate to execute the first AI task.

[0126] The task policy information can indicate a task requirement. For example, the first AI task can be a model training task, and the task requirement can include a capability requirement of a model, such as an accuracy requirement of an inference result of the model, a latency requirement of inference, and the like. For another example, the first AI task can be a model inference task, such as a requirement of model selection, a requirement of task allocation, and the like. The current task policy information in the related information of the first AI task can indicate a current task requirement of the first AI task.

[0127] The task policy information can indicate a computing queue priority and / or a resource allocation manner. The current task policy information in the related information of the first AI task can indicate a current computing queue priority and / or a resource allocation manner of the first AI task. For example, the first AI task can include multiple subtasks or multiple computing processes. The computing queue priority includes a priority of executing each subtask and / or a priority of executing each computing process. The resource allocation manner can be an allocation manner of a computing resource and / or a storage resource. The computing resource can be a computing unit core, including but not limited to one or more of a central processing unit (CPU), a graphics processing unit (GPU), or a neural processing unit (NPU). The storage resource can include one or more of a memory, a display memory, or a cache.

[0128] The related information of the first AI task can further include initial configuration information of the task. The initial configuration information can be determined through signaling interaction and negotiation among multiple nodes of a CU, a SU, an AMF node, or a server. The initial configuration information can include at least one of a model identifier or a distributed execution rule of the model. For example, the distributed execution rule of the model can include a decomposition manner, an allocation manner, a service logic among multiple nodes, and the like, of a submodel and / or a subtask.

[0129] If the first communication device needs to perform joint optimization of communication and calculation according to the capability information of the first node, the first communication device can obtain the capability information of the first node.

[0130] For example, the first communication device can be a node providing an AI service. If the first communication device is an SU, the SU can monitor the execution state of the node performing the first AI task (including the first node) and obtain the capability information of the node performing the first AI task.

[0131] For another example, the first communication device can be a CU, and the CU can receive the capability information of the first node from the SU.

[0132] Exemplarily, the capability information of the first node can include, but is not limited to, at least one of the computing capability of the first node, and the progress information of the currently running task.

[0133] The computing capability of the first node can be at least one of the computing power occupation of the first node and the remaining computing power. If the first node is currently running at least one task, the capability information of the first node can include the progress information of the at least one task, and / or the proportion of the computing power of the first node occupied by each task, etc.

[0134] Specifically, the first communication device can take the transmission parameter of the air interface as a constraint item of joint optimization, and optionally, the constraint item of joint optimization can also include the second QoS requirement parameter. The first communication device combines at least one of the related information of the first AI task or the capability information of the first node to solve the joint optimization problem of communication and calculation, and obtains the respective optimized results of communication and calculation, i.e., the first task strategy information and the first QoS requirement parameter. According to this scheme, the global optimization of communication and calculation can be combined in mechanism, and the task strategy and the QoS requirement parameter closer to the optimal solution can be obtained, which can improve the communication efficiency and the AI service quality, and the result obtained by executing the AI task is applied to the communication service and / or the third-party application, so that the communication efficiency of the communication system and the service quality of the system can be improved.

[0135] S503, the first communication device sends second information, the second information being used to indicate the first QoS requirement parameter.

[0136] For example, the first communication device can be the SU, after the SU determines the first task policy information and the first QoS requirement parameter, the SU can update the task policy of the first AI task according to the first task policy information. And the SU can send the second information to the CU, through which the CU is informed of the first QoS requirement parameter, and the CU can inform the DU of the first QoS requirement parameter, so that the air interface applies the first QoS requirement parameter. In one possible implementation, the CU sends the sixth information to the access and mobility management function node, and the sixth information is used to indicate the first QoS requirement parameter. The CU informs the access and mobility management function node through the sixth information that the updated QoS requirement parameter is the first QoS requirement parameter, and the access and mobility management function node can forward the first QoS requirement parameter to the session management function node, and the SMF node informs the terminal through the non-access stratum (NAS) message that the updated QoS requirement parameter is the first QoS requirement parameter. Exemplarily, the access and mobility management function can be an AMF, or a node with similar functions to realize the functions of the AMF node. The session management function can be an SMF, or a node with similar functions to realize the functions of the AMF node. That is, the second communication device can realize that the updated QoS requirement parameter can be delivered to the terminal by sending the sixth information.

[0137] For another example, the first communication device is the CU, after the CU determines the first task policy information and the first QoS requirement parameter, the CU can send the first task policy information to the SU, and the SU updates the task policy corresponding to the first AI task according to the first task policy information. And the CU can inform the DU of the first QoS requirement parameter, so that the air interface applies the first QoS requirement parameter. The CU also sends the second information to the AMF node, through which the AMF node is informed that the updated QoS requirement parameter is the first QoS requirement parameter. The AMF node can forward the first QoS requirement parameter to the SMF node, and the SMF node informs the terminal through the NAS message that the updated QoS requirement parameter is the first QoS requirement parameter.

[0138] After the DU and the terminal obtain the updated QoS requirement parameter, the two ends of the air interface (i.e. the access network node and the terminal) obtain the updated first QoS requirement parameter, and the DU can determine the data transmission strategy according to the first QoS requirement parameter, so that when the DU and the terminal transmit the data related to the first AI task through the air interface, the first QoS requirement parameter can be met.

[0139] Optionally, in S502, the first communication device determines the first task policy information corresponding to the first AI task and the first QoS requirement parameter corresponding to the first AI task, including: the first communication device determines at least one task policy information corresponding to the first AI task and at least one candidate QoS requirement parameter corresponding to the first AI task. The at least one task policy information includes the first task policy information, and the at least one candidate QoS requirement parameter includes the first QoS requirement parameter.

[0140] In the embodiment 1, the first communication device determines the at least one task policy information and the plurality of candidate QoS requirement parameters.

[0141] In this optional embodiment, the first communication device can be a SU. The SU can determine the at least one task policy information and the plurality of candidate QoS requirement parameters according to the first information, and according to the related information of the first AI task or the capability information of the first node.

[0142] In the example 1-1, the at least one task policy information is one task policy information, i.e., the first task policy information. The SU determines the first task information and the plurality of candidate QoS requirement parameters, wherein the task policy indicated by the first task policy information supports the plurality of candidate QoS requirement parameters. Or in other words, when the first AI task adopts the task policy indicated by the first task policy information, any one of the plurality of candidate QoS requirement parameters can be applied by the air interface to implement the first AI task. The QoS requirement parameter applied by the air interface refers to the QoS requirement parameter that needs to be met when the air interface transmits the data related to the first AI task. The SU can update the task policy of the first AI task according to the first task policy information, and the SU sends second information to the CU, wherein the second information is specifically used to indicate the plurality of candidate QoS requirement parameters determined by the SU. The CU can determine the first QoS requirement parameter from the plurality of candidate QoS requirement parameters, i.e., the first QoS requirement parameter is used as the QoS requirement parameter that needs to be met when the air interface transmits the data related to the first AI task. Optionally, the CU can send third information to the SU, wherein the third information is used to indicate the first QoS requirement parameter applied by the air interface. However, the present application is not limited thereto, and the CU can also not notify the SU of the QoS requirement parameter applied by the air interface.

[0143] In Example 1-2, the at least one task policy information includes a plurality of task policy information, and the plurality of task policy information corresponds to a plurality of candidate QoS requirement parameters. One task policy information can correspond to one or more candidate QoS requirement parameters. The SU can send second information to the CU, where the second information is specifically used to indicate the plurality of candidate QoS requirement parameters determined by the SU. The SU can receive third information from the CU, where the third information is used to indicate the first QoS requirement parameter applied by the air interface. The SU can determine, according to the first QoS requirement parameter, that the task policy information corresponding to the first QoS requirement parameter is the first task policy information, and then update the task policy of the first AI task according to the first task policy information.

[0144] According to the above scheme, the SU can provide the CU with a plurality of candidate QoS requirement parameters, so that the CU can determine more suitable QoS requirement parameters based on the actual situation of the access network and the air interface. The performance of the communication and computing joint optimization is further improved.

[0145] In Embodiment 2, the first communication device determines a plurality of task policy information and at least one candidate QoS requirement parameter.

[0146] In this optional embodiment, the first communication device can be the CU. The CU can determine the plurality of task policy information and the at least one candidate QoS requirement parameter according to the first information and according to the related information of the first AI task or the capability information of the first node.

[0147] In Example 2-1, the at least one candidate QoS requirement parameter is one QoS requirement parameter, i.e., the first QoS requirement parameter. The plurality of task policy information all support the first QoS requirement parameter. After the CU determines the first QoS requirement parameter and the plurality of task policy information, the CU can send seventh information to the SU, where the seventh information is used to indicate the plurality of task policy information determined by the CU. The SU can determine, from the plurality of task policy information, the first task policy information adopted by the first AI task, and update the task policy of the first AI task with the first task policy information. After the SU determines the first task policy information, the SU can notify the CU of the task policy indicated by the first task policy information adopted by the first AI task, or the SU can not notify the CU, which is not limited in the present application.

[0148] In Example 2-2, the at least one QoS requirement parameter includes a plurality of QoS requirement parameters, and the plurality of task policy information corresponds to the plurality of QoS requirement parameters, where one QoS requirement parameter corresponds to one or more task policy information. The CU can send, to the SU, seventh information, where the seventh information indicates that the CU determines the plurality of task policy information. The SU can send, to the CU, eighth information, where the eighth information indicates the first task policy information. The CU determines that the first QoS requirement parameter corresponds to the first task policy information, and the CU determines that the first QoS requirement parameter is applied to the air interface.

[0149] According to the above scheme, the CU can provide the SU with the plurality of task policy information, so that the SU can determine more suitable task policy information according to the actual situation of the first AI task. The performance of the communication and computing joint optimization is further improved.

[0150] To sum up, the scheme provided by the embodiments of the present application can combine communication and computing for global joint optimization, balance the efficiency and quality of communication and computing, obtain an AI task policy and a communication QoS requirement parameter that are closer to the optimal solution, improve the efficiency and quality of communication and computing, and apply the result of executing the AI task to a communication service and / or a third-party application, thereby improving the communication efficiency of the communication system and the service quality of the system.

[0151] FIG. 6 is a schematic flowchart of a communication method 600 provided by an embodiment of the present application. In the following, the implementation manner when the first communication device in the embodiment shown in FIG. 4 is the SU will be specifically introduced by taking the communication method 600 shown in FIG. 6 as an example. It should be noted that the same parts in the embodiment shown in FIG. 6 as in the embodiment shown in FIG. 4 can be implemented by referring to the foregoing description of the embodiment shown in FIG. 4, and for brevity, will not be described here again.

[0152] S601, the CU sends, to the SU, first information, where the first information is used to indicate a transmission parameter of an air interface.

[0153] Correspondingly, the SU receives the first information from the CU, and determines the transmission parameter of the air interface according to the first information.

[0154] Optionally, the CU can receive the transmission parameter of the air interface reported by the DU, and the CU sends the first information to the SU to indicate the transmission parameter of the air interface.

[0155] Optionally, before S601, in a data channel establishment process of the first AI task, the AMF can send, to the CU, a third QoS requirement parameter, where the third QoS requirement parameter is a QoS requirement parameter that needs to be met when the access network node and the terminal transmit related data of the first AI task through the air interface. The CU can notify the DU to adopt the third QoS requirement parameter.

[0156] Optionally, the first information is further used to indicate a second QoS requirement parameter, i.e., a QoS requirement parameter currently applied by the air interface.

[0157] If the QoS requirement parameter applied by the air interface is not updated after the data channel establishment process of the first AI task, the second QoS requirement parameter is the third QoS requirement parameter described above, and if the QoS requirement parameter applied by the air interface is updated after the data channel establishment process of the first AI task, the second QoS requirement parameter is the QoS requirement parameter updated by the air interface last time.

[0158] S602, the SU determines, according to the first information and at least one of the related information of the first AI task or the capability information of the first node, the first task policy information corresponding to the first AI task and the first QoS requirement parameter corresponding to the first AI task, the first node being a node executing the first AI task, the first task policy information being used to indicate a task policy of the first AI task, and the first QoS requirement parameter being a candidate QoS requirement parameter for the air interface to transmit data related to the first AI task.

[0159] The SU performs joint optimization of communication and calculation according to the first information and at least one of the related information of the first AI task or the capability information of the first node, and obtains a result of the joint optimization, including the first task policy information corresponding to the calculation (i.e., the first AI task) and the first QoS requirement parameter corresponding to the communication (i.e., the transmission of data related to the first AI task). The global optimization of joint communication and calculation can improve the communication efficiency and the AI service quality, and the result obtained by executing the AI task is applied to the communication service and / or the third-party application, so as to improve the communication efficiency of the communication system and the service quality of the system.

[0160] S603, the SU sends second information to the CU, the second information being used to indicate the first QoS requirement parameter.

[0161] The SU sends the second information to the CU to inform that the updated QoS requirement parameter is the first QoS requirement parameter, and the SU can update the task policy of the first AI task according to the first task policy information. It should be understood that the execution sequence of the SU updating the task policy of the first AI task and S603 is not limited in the embodiments of the present application.

[0162] Correspondingly, the CU receives the second information from the SU, and can determine the first QoS requirement parameter according to the second information. The CU informs the DU that the updated QoS requirement parameter is the first QoS requirement parameter.

[0163] Optionally, the SU determines the first task policy information corresponding to the first AI task and the first QoS requirement parameter corresponding to the first AI task, including: the SU determines at least one task policy information corresponding to the first AI task and a plurality of candidate QoS requirement parameters corresponding to the first AI task. The at least one task policy information includes the first task policy information, and the plurality of candidate QoS requirement parameters include the first QoS requirement parameter.

[0164] In this optional implementation, the second information specifically indicates a plurality of candidate QoS requirement parameters determined by the SU. The CU can determine a QoS requirement parameter, such as the first QoS requirement parameter, for the air interface from the plurality of candidate QoS requirement parameters indicated by the second information. The CU can or can not notify the SU after determining the first QoS requirement parameter. For details, reference can be made to the foregoing embodiment 1, examples 1-1 and 1-2, which will not be repeated here.

[0165] Optionally, at S604, the CU sends sixth information to the AMF node, where the sixth information is used to indicate the first QoS requirement parameter.

[0166] Correspondingly, the AMF node receives the sixth information from the CU, and determines that the QoS requirement parameter of the air interface is updated to the first QoS requirement parameter according to the sixth information. The AMF node can update the QoS requirement parameter to the UE through the SMF node.

[0167] The DU determines that the updated QoS requirement parameter is the first QoS parameter through the CU, and the terminal can determine that the updated QoS requirement parameter is the first QoS parameter through the sixth information sent by the CU to the AMF node and the information transmitted by the SMF node, so that the two ends (i.e., the DU and the terminal) of the air interface obtain the updated first QoS requirement parameter. The DU can determine a data transmission strategy according to the first QoS requirement parameter, so that the DU and the terminal can meet the first QoS requirement parameter when transmitting data related to the first AI task through the air interface.

[0168] According to the above scheme, the SU can perform global optimization of joint communication and calculation, balance the efficiency and quality of communication and calculation, obtain AI task strategy and communication QoS requirement parameter closer to the optimal solution, improve the efficiency and quality of communication and calculation, and apply the result of executing the AI task to communication services and / or third-party applications, thereby improving the communication efficiency of the communication system and the service quality of the system.

[0169] FIG. 7 is a schematic flow chart of a communication method 700 according to an embodiment of the present application. The following will take the communication method 700 shown in FIG. 7 as an example to specifically introduce the implementation manner when the first communication device in the embodiment shown in FIG. 4 is the CU. It should be noted that the same parts in the embodiment shown in FIG. 7 as those in the embodiments shown in FIG. 4 and FIG. 6 can be implemented by referring to the foregoing description of the embodiments shown in FIG. 4 and FIG. 6, and for brevity, will not be described here again.

[0170] S701. The SU sends fifth information to the CU, where the fifth information is used to indicate the related information of the first AI task and / or the capability information of the first node.

[0171] Correspondingly, the CU receives the fifth information from the SU, and determines the related information of the first AI task and / or the capability information of the first node according to the fifth information.

[0172] S702. The CU determines the first task policy information corresponding to the first AI task and the first QoS requirement parameter corresponding to the first AI task according to the first information and the fifth information.

[0173] Optionally, the CU can receive the transmission parameter of the air interface reported by the DU, and the first information indicates the transmission parameter of the air interface.

[0174] Optionally, before S701, during the data channel establishment process of the first AI task, the AMF can send third QoS requirement parameter to the CU, where the third QoS requirement parameter is a QoS requirement parameter that needs to be met when the access network node and the terminal transmit the related data of the first AI task through the air interface. The CU can notify the DU to use the third QoS requirement parameter.

[0175] The CU performs joint optimization of communication and calculation according to the first information and at least one of the related information of the first AI task or the capability information of the first node, to obtain a joint optimization result, including the first task policy information corresponding to the calculation (i.e., the first AI task) and the first QoS requirement parameter corresponding to the communication (i.e., the transmission of the related data of the first AI task). The global optimization of joint communication and calculation can improve the communication efficiency and the quality of service of the AI, and the result obtained by executing the AI task can be applied to the communication service and / or the third-party application, so as to improve the communication efficiency of the communication system and the quality of service of the system.

[0176] S703. The CU sends seventh information to the SU, where the seventh information is used to indicate the first task policy information.

[0177] Correspondingly, the SU receives the seventh information from the CU, and determines the first task policy information according to the seventh information. The SU updates the task policy of the first AI task according to the first task policy information.

[0178] Optionally, the CU determines the first task policy information corresponding to the first AI task and the first QoS requirement parameter corresponding to the first AI task, including: the CU determines a plurality of task policy information corresponding to the first AI task and at least one candidate QoS requirement parameter corresponding to the first AI task. The plurality of task policy information includes the first task policy information, and the at least one candidate QoS requirement parameter includes the first QoS requirement parameter.

[0179] In this optional implementation, the seventh information specifically indicates a plurality of task policy information determined by the CU. The SU can determine one task policy information, such as the first task policy information, from the plurality of task policy information indicated by the seventh information, so that the SU updates the task policy of the first AI task according to the first task policy information. After determining the first task policy information, the SU can or can not notify the CU. For details, please refer to the foregoing example 2-1 and example 2-2 in the implementation 2, which will not be repeated here.

[0180] Optionally, in S704, the CU sends second information to the AMF node, where the second information is used to indicate the first QoS requirement parameter.

[0181] Correspondingly, the AMF node receives the second information from the CU, and determines that the QoS requirement parameter of the air interface is updated to the first QoS requirement parameter according to the second information. The AMF node can update the QoS requirement parameter to the UE through the SMF node.

[0182] After the DU and the terminal obtain the updated QoS requirement parameter, the DU can determine a data transmission strategy according to the first QoS requirement parameter, so that when the DU and the terminal transmit data related to the first AI task through the air interface, the first QoS requirement parameter can be met.

[0183] According to the above scheme, the CU can perform global optimization of joint communication and calculation, balance the efficiency and quality of communication and calculation, obtain AI task policy and communication QoS requirement parameter closer to the optimal solution, improve the efficiency and quality of communication and calculation, and apply the result of executing the AI task to the communication service and / or the third-party application, thereby improving the communication efficiency of the communication system and the service quality of the system.

[0184] In an optional implementation, after the CU notifies the DU of the updated QoS requirement parameter, if the DU cannot meet the updated QoS requirement parameter, the DU can feed back that it cannot meet the updated QoS requirement parameter, so as to trigger reconfiguration of the first AI task.

[0185] Exemplarily, in a case that a server (such as an application (APP) server, or a cloud server) participates in the first AI task, the DU can not be able to meet the updated QoS requirement parameter due to unreasonable initial configuration of the first AI task, and therefore, the DU can feed back to trigger reconfiguration of the first AI task. The following is described in combination with FIG. 8.

[0186] FIG. 8 is a schematic flowchart of a communication method 800 provided by an embodiment of the present application. The communication method 800 includes but is not limited to the following S801 to S805.

[0187] S801, the DU sends fourth information, which is used to indicate that the updated QoS transmission parameter cannot be met.

[0188] Before S801, the DU receives the updated QoS transmission parameter obtained by the communication and computing joint optimization from the CU, and the DU determines that the QoS transmission parameter cannot be met, and the DU can perform S801. The fourth information can also be understood as indicating that the communication and computing joint optimization fails. The present application does not limit this.

[0189] Specifically, the DU can send the fourth information to the CU, and the CU reports to the AMF or the SU that the DU determines that the QoS transmission parameter obtained by the joint optimization cannot be met, so that the AMF or the SU triggers reconfiguration of the first AI task. Alternatively, the DU can send the fourth information to the SU, and the SU can trigger reconfiguration of the first AI task.

[0190] S802, the CU, the SU, the AMF node and the server perform a reconfiguration process of the first AI task.

[0191] By performing the reconfiguration process of the first AI task by the CU, the SU, the AMF node and the server, the scheduling configuration information of the first AI task and the obtained QoS requirement parameter after reconfiguration, such as the fourth QoS requirement parameter, are obtained. The scheduling configuration information of the first AI task can indicate the division manner of the first AI task, such as the task division manner of the server, the terminal and the access network, and can also indicate other scheduling information of the first AI task.

[0192] In an implementation, the DU sends the fourth information to the CU in S801, the CU can initiate a task reconfiguration to the SU, specifically, the CU can send a task reconfiguration request (or trigger) information to the SU, the task reconfiguration request information is used to indicate that the communication and computing joint optimization process fails. Optionally, the task reconfiguration request information can include indication information, which is used to indicate the reason for the failure of the communication and computing joint optimization process. As the failure reason can be at least one of that the updated QoS requirement parameter cannot be met by the air interface or that the initial configuration of the first AI task is unreasonable. The SU can perform a task reconfiguration according to the task reconfiguration request information, the task reconfiguration but not limited to determining one or more of the following: task execution mode (such as can be performed by one of the terminal side, network side, server alone or multiple cooperation to perform the first AI task), and distributed execution rules in the case of multiple nodes participating in the execution of the first AI task, such as the aforementioned distributed execution rules can include the decomposition mode, allocation mode, business logic between multiple nodes of the sub-model of the model and / or the sub-task of the task. Further, the SU can notify the core network to perform QoS reconfiguration, so that the nodes (such as AMF nodes) in the core network can determine the QoS requirement parameter after performing the task reconfiguration in S803 through the ninth information to the CU.

[0193] Optionally, the SU can perform the task reconfiguration jointly with the server according to the task reconfiguration request information. In this optional way, the core network can be notified by the SU or the server to perform QoS reconfiguration.

[0194] In another implementation, the DU sends the fourth information to the SU in S802, then the SU can perform the task reconfiguration according to the fourth information, or the SU can perform the task reconfiguration jointly with the server according to the fourth information. And the core network can be notified by the SU or the server to perform QoS reconfiguration.

[0195] In S803, the AMF node sends the ninth information to the CU, the ninth information is used to indicate the fourth QoS requirement parameter.

[0196] Correspondingly, the CU receives the ninth information from the AMF node, and determines the fourth QoS requirement parameter, i.e. the reconfigured QoS requirement parameter, according to the ninth information.

[0197] In S804, the CU and the SU perform the communication and computing joint optimization process and optimization result delivery.

[0198] The CU and the SU perform the communication and computing joint optimization process and optimization result delivery, and optionally, the DU also participates in the communication and computing joint optimization process.

[0199] The specific implementation of S804 can be implemented by a method provided by an embodiment as shown in FIG. 6. Alternatively, it can be implemented by a method provided by an embodiment as shown in FIG. 7.

[0200] According to the above scheme, when the DU cannot meet the QoS requirement parameter obtained by joint optimization of communication and calculation, the reconfiguration process of the first AI task can be triggered by feedback. The situation that the data transmission quality related to the first AI task is reduced due to the DU being unable to meet the updated QoS requirement parameter can be avoided, and the system reliability is improved.

[0201] It should be noted that in the embodiments of the present application, the architecture of the access network adopting DU and CU separation is taken as an example for description, and it should be understood that the present application is not limited thereto, and the embodiments of the present application can also be applied to the architecture of DU and CU not being separated, for example, DU and CU belong to the same access network node, and then the operations performed by DU and CU in the above embodiments are performed by the access network node.

[0202] It can be understood that, in order to realize the functions in the above embodiments, the network device includes the hardware structure and / or software module corresponding to each function. Those skilled in the art should easily realize that, in combination with the units and method steps of the examples described in the embodiments disclosed in the present application, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in the form of hardware or computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0203] FIGS. 9 and 10 are structural schematic diagrams of possible communication apparatuses provided by embodiments of the present application. These communication apparatuses can be used to realize the functions of the DU, CU, SU or AMF node in the above method embodiments, and thus can also realize the beneficial effects possessed by the above method embodiments. In the embodiments of the present application, the communication apparatus can be the RAN node as shown in FIGS. 1 to 4, or can be a module (such as a chip or a chip system or a logic circuit) applied to the RAN node as shown in FIGS. 1 to 4, and the RAN node can be a DU, a CU or a SU. Alternatively, the communication apparatus can be the core network node as shown in FIGS. 1 to 4, or can be a module (such as a chip or a chip system or a logic circuit) applied to the core network node as shown in FIGS. 1 to 4, and the core network node can be an AMF node or an SMF node.

[0204] The communication apparatus 900 includes a transceiver unit 920, which can be used to receive or send information, and the communication apparatus 900 can also include a processing unit 910, which can be used to process instructions or data to realize corresponding operations.

[0205] It should be understood that when the communication apparatus 900 is a chip configured in (or used for) a communication device, the transceiver unit 920 in the communication apparatus 900 can be an input / output interface or circuit of the chip, and the processing unit 910 in the communication apparatus 900 can be a processor in the chip.

[0206] Optionally, the communication apparatus 900 can further include a storage unit 930, which can be used to store instructions or data, and the processing unit 910 can execute the instructions or data stored in the storage unit to enable the communication apparatus to implement corresponding operations.

[0207] The communication apparatus 900 can be used to implement the functions of the first communication apparatus in the method embodiments shown in FIGS. 5 to 8.

[0208] When the communication apparatus 900 is used to implement the functions of the first communication apparatus in the method embodiments shown in FIGS. 5 to 8: the processing unit 910 is configured to obtain first information, the first information being used to indicate a transmission parameter of an air interface. The processing unit 910 is further configured to determine, according to the first information and according to at least one of related information of a first artificial intelligence (AI) task or capability information of a first node, first task policy information corresponding to the first AI task and first quality of service (QoS) requirement parameters corresponding to the first AI task, wherein the first node is a node that executes the first AI task, the first task policy information is used to indicate a task policy of the first AI task, and the first QoS requirement parameters are candidate QoS requirement parameters for the air interface to transmit data related to the first AI task. The transceiver unit 920 is configured to send second information, the second information being used to indicate the first QoS requirement parameters.

[0209] The communication apparatus 900 is configured to implement the functions of a second communication apparatus, which can be the CU in the embodiment shown in FIG. 6.

[0210] When the second communication apparatus is used to implement the functions of the CU in the method embodiment shown in FIG. 6: the transceiver unit 920 is configured to send first information, the first information being used to indicate a transmission parameter of an air interface. The transceiver unit 920 is further configured to receive second information, the second information being used to indicate first QoS requirement parameters, the first QoS requirement parameters being QoS requirement parameters for the air interface to transmit data related to a first AI task, the first QoS requirement parameters being obtained according to the first information and according to at least one of related information of the first AI task or capability information of the first node. The processing unit 920 is configured to determine, according to the second information, the first QoS requirement parameters.

[0211] The communication apparatus 900 is configured to implement the functions of a second communication apparatus, which can be the SU in the embodiment shown in FIG. 7.

[0212] When the second communication device is configured to implement the function of the SU in the method embodiment shown in FIG. 7, the processing unit 910 is configured to determine fifth information, the fifth information including related information of the first AI task and / or capability information of the first node, the first node being a node providing an AI service. The transceiver unit 920 is configured to send the fifth information. The transceiver unit 920 is further configured to receive first task policy information, the first task policy information being used to indicate a task policy of the first artificial intelligence (AI) task, the first task policy being obtained according to a transmission parameter of an air interface and the fifth information.

[0213] For more detailed description of the processing unit 910 and the transceiver unit 920, please refer to the related description in the method embodiments shown in FIGS. 5-8.

[0214] It should be understood that the transceiver unit 920 in the communication device 900 can be implemented through a communication interface (such as a transceiver, a transceiver circuit, an input / output interface, or a pin, etc.). When the communication interface is a transceiver, the transceiver can be composed of a receiver and / or a transmitter. The processing unit 910 in the communication device 900 can be implemented through at least one processor, and the processing unit 910 in the communication device 900 can also be implemented through at least one logic circuit. Optionally, the communication device 900 further includes a storage unit, which can be implemented by a memory.

[0215] As shown in FIG. 10, the communication device 1000 includes a processor 1010 and an interface circuit 1020. The processor 1010 and the interface circuit 1020 are coupled to each other. It can be understood that the interface circuit 1020 can be a transceiver or an input / output interface. Optionally, the communication device 1000 can further include a memory 1030 for storing instructions executed by the processor 1010 or storing input data required by the processor 1010 to run instructions or storing data generated after the processor 1010 runs instructions.

[0216] In an implementation manner, the memory 1030 can also be integrated in the processor 1010 or independent of the processor 1010.

[0217] When the communication device 1000 is configured to implement the method shown in FIG. 5, the processor 1010 is configured to implement the function of the processing unit 910 described above, and the interface circuit 1020 is configured to implement the function of the transceiver unit 920 described above.

[0218] When the communication device is a module applied to a network device, the network device module can implement the functions of the first communication device in the method embodiments. The network device module receives information from other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by a terminal device to the network device; or the network device module sends information to other modules (such as a radio frequency module or an antenna) in the network device, and the information is sent by the network device to the terminal device. The network device module herein can be a baseband chip of the network device, or an SU, a CU, a DU or other modules, and the CU and the DU herein can be an O-CU and an O-DU under an open radio access network (O-RAN) architecture.

[0219] It can be understood that the processor in the embodiments of the present application can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), microprocessor units (MPUs), microcontroller units (MCUs), graphics processing units (GPUs), artificial intelligence processors (AI processors), neural processing units (NPUs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The general-purpose processor can be a microprocessor or any conventional processor.

[0220] The method steps in the embodiments of the present application can be implemented in hardware or in software instructions executable by a processor. The software instructions can be composed of corresponding software modules, which can be stored in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, a register, a hard disk, a mobile hard disk, a CD-ROM, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor, so that the processor can read information from and write information to the storage medium. The storage medium can also be an integral part of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in an access network device or a terminal device. The processor and the storage medium can also exist as discrete components in the access network device or the terminal device.

[0221] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer program product, which comprises computer program codes, and when the computer program codes are executed by one or more processors, the device comprising the processors executes the method provided in the embodiments shown in FIG. 5 to FIG. 8.

[0222] In the above embodiments, the implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented by using software, the implementation can be in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer programs or instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are entirely or partially executed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, or other programmable apparatus.

[0223] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a computer readable storage medium, which stores the above computer program or instructions, and when the computer program or instructions are run by one or more processors, the device comprising the processors executes the method provided in the embodiments shown in FIG. 5 to FIG. 8.

[0224] The computer program or instructions can be stored in or transferred from one computer-readable medium to another computer-readable medium, e.g., from one website, computer, server or data center to another website, computer, server or data center, through wired or wireless ways. The computer-readable medium can be any available medium or data storage device that can be accessed by a computer, or a data storage device such as a server, data center, etc. that integrates one or more available media. The available media can be a magnetic medium, such as a floppy disk, a hard disk, a magnetic tape; an optical medium, such as a digital video disc; or a semiconductor medium, such as a solid-state disk. The computer-readable medium can be a volatile or non-volatile storage medium, or can include both volatile and non-volatile storage media.

[0225] According to the method provided in the embodiments of the present application, the embodiments of the present application further provide a communication system, which comprises one or more first communication devices described above. The system can further comprise one or more second communication devices. The first communication device can be a CU in the method embodiments or a module capable of realizing the functions / operations of the CU, and the second communication device can be a SU in the method embodiments or a module capable of realizing the functions / operations of the SU. Alternatively, the first communication device can be a SU or a module capable of realizing the functions / operations of the SU, and the second communication device can be a CU in the method embodiments or a module capable of realizing the functions / operations of the CU.

[0226] In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device described above is only illustrative. For example, the division of the units is only a logical function division. There can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0227] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e. they can be located in one place or distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the present application.

[0228] In various embodiments of the present application, the terms and / or descriptions among different embodiments are consistent and can be referred to each other if there is no special description and logical conflict, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0229] The above merely provides the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of the changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method comprises: obtaining first information, the first information being used to indicate a transmission parameter of an air interface; determining, according to the first information and at least one of related information of a first artificial intelligence (AI) task or capability information of a first node, first task policy information corresponding to the first AI task and a first quality of service (QoS) requirement parameter corresponding to the first AI task, wherein the first node is a node performing the first AI task, the first task policy information is used to indicate a task policy of the first AI task, and the first QoS requirement parameter is a candidate QoS requirement parameter for the air interface to transmit data related to the first AI task; sending second information, the second information being used to indicate the first QoS requirement parameter.

2. The method of claim 1, wherein, The transmission parameter comprises a transmission state parameter and / or a transmission capability parameter of the air interface, wherein the transmission state parameter comprises one or more of the following transmission state parameters of the air interface transmitting data related to the first AI task: a transmission rate, a transmission delay, a packet loss rate, a predicted value of the transmission rate, a predicted value of the transmission delay, or a predicted value of the packet loss rate; The transmission capability parameter comprises one or more of the following transmission parameters supported by the air interface: a maximum transmission rate supported, a minimum transmission delay supported, or a minimum packet loss rate.

3. The method according to claim 1 or 2, characterized in that, The capability information of the first node comprises one or more of the following: a computing capability or progress information of a currently running task.

4. The method according to any one of claims 1 to 3, characterized in that, The first task policy information is used to indicate one or more of the following task policies: a task execution mode, a task requirement, a computing queue priority, or a resource allocation mode.

5. The method according to any one of claims 1 to 4, characterized in that, The first information is also used to indicate a second QoS requirement parameter, which is a QoS requirement parameter corresponding to data related to the first AI task.

6. The method according to any one of claims 1 to 5, characterized in that, The related information of the first AI task comprises one or more of the following: current execution progress information, current task policy information, or initial configuration information of a task.

7. The method according to any one of claims 1 to 6, characterized in that, The method further comprises: determining configuration information of the first AI task according to the first task policy information; and sending the configuration information to the first node.

8. The method according to any one of claims 1 to 7, characterized in that, The determination of the first task policy information and the first QoS requirement parameter comprises: determining at least one task policy information and a plurality of candidate QoS requirement parameters, the at least one task policy information comprising the first task policy information, and the plurality of candidate QoS requirement parameters comprising the first QoS requirement parameter, wherein the second information is used to indicate the plurality of candidate QoS requirement parameters.

9. The method of claim 8, wherein, The at least one task policy information is the first task policy information, and the task policy indicated by the first task policy information supports the plurality of candidate QoS requirement parameters.

10. The method of claim 8, wherein, The at least one task policy information comprises a plurality of task policy information, the plurality of task policy information corresponding to the plurality of candidate QoS requirement parameters, and the method further comprises: receiving third information, the third information being used to indicate the first QoS requirement parameter in the plurality of candidate QoS requirement parameters, the first QoS requirement parameter being a QoS requirement parameter of the air interface application; determining the first task policy information according to the first QoS requirement parameter, the first task policy information being task policy information corresponding to the first QoS requirement parameter in the plurality of task policy information.

11. The method according to any one of claims 1 to 9, characterized in that, Before the obtaining the first information, the method comprises: receiving fourth information, the fourth information being used to indicate that the air interface cannot meet the updated QoS requirement parameter.

12. The method according to any one of claims 1 to 11, characterized in that, The method further comprises: receiving fifth information, the fifth information comprising related information of the first AI task and / or capability information of the first node; sending the first task policy information.

13. A communication method, comprising: sending first information, the first information being used to indicate a transmission parameter of an air interface; receiving second information, the second information being used to indicate a first QoS requirement parameter, the first QoS requirement parameter being a QoS requirement parameter of the air interface for transmitting data related to a first AI task, the first QoS requirement parameter being obtained according to at least one of the first information and related information of the first AI task or capability information of a first node.

14. The method of claim 13, wherein, The first information is further used to indicate a second QoS requirement parameter, the second QoS requirement parameter being a QoS requirement parameter corresponding to current data related to the first AI task.

15. The method according to claim 13 or 14, characterized in that, The method further comprises: sending sixth information to an access and mobility management function node, the sixth information being used to indicate the first QoS requirement parameter, the first QoS requirement parameter being an updated QoS requirement parameter of the air interface application.

16. A method of communication, comprising: The method comprises: sending fifth information, the fifth information comprising related information of the first AI task and / or capability information of the first node, the first node being a node providing an AI service; receiving first task policy information, the first task policy information being used to indicate a task policy of the first AI task, the first task policy being obtained according to a transmission parameter of an air interface and the fifth information.

17. The method of claim 16, wherein, The method further comprises: determining configuration information of the first AI task according to the first task policy information; sending the configuration information to the first node.

18. The method of claim 16 or 17, wherein, The first task policy information is used to indicate one or more of the following task policies: a task execution mode, a task requirement, a computing queue priority, or a resource allocation mode.

19. The method according to any one of claims 13 to 18, characterized in that, The transmission parameter comprises a transmission state parameter and / or a transmission capability parameter of the air interface, The transmission state parameter comprises one or more of the following transmission state parameters of the air interface for transmitting data related to the first AI task: a transmission rate, a transmission delay, a packet loss rate, a predicted value of the transmission rate, a predicted value of the transmission delay, or a predicted value of the packet loss rate; The transmission capability parameter comprises one or more of the following transmission parameters supported by the air interface: a maximum transmission rate supported, a minimum transmission delay supported, or a minimum packet loss rate.

20. The method of any one of claims 13-19, wherein, The capability information of the first node comprises one or more of: a computing capability, or progress information of a currently running task.

21. The method according to any one of claims 13 to 20, characterized in that, The related information of the first AI task comprises one or more of: current execution progress information, current task policy information, or initial configuration information of the task.

22. A communications device, characterized by comprise a processor, The processor is coupled with a memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory; and / or the processor is through a logic circuit, so that the communication device executes the method in any one of claims 1-21.

23. A computer-readable storage medium, characterized in that, instructions stored thereon, when executed on a computer, cause the computer to perform the method of any one of claims 1-21.

24. A computer program product, characterised in that, The computer program product comprises a computer program, when the computer program is executed, causes a computer to execute the method of any one of claims 1-21.

25. A communications device, characterized by comprise a module or unit for executing the method of any one of claims 1-21.

Images