Communication method and apparatus

Abstract

The present application provides a communication method and apparatus, for use in solving the problems that in the calling of existing data analysis functions, when fixed interaction processes and related parameters are applied to scenarios such as different network states or different terminal states, network resource waste or service quality degradation may be caused, and adaptability is poor. The method comprises: a first network element receives a first message from a second network element, the first message being used for requesting to perform task decomposition on at least one service request; the first network element acquires a task decomposition result corresponding to the service request, the task decomposition result comprising identification information of one or more service functions, wherein the task decomposition result is obtained on the basis of an artificial intelligence (AI) model, and the service function is used for implementing a corresponding data processing function; and the first network element sends the task decomposition result to the second network element.

Description

Communication method and device

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office on December 20, 2023, with application number 202311774029.0 and application name “A Communication Method and Device”, the entire contents of which are incorporated by reference into this application. Technical Field

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

[0003] In response to the increasing complexity of current communication scenarios, the diversification of service requirements, and the personalized service experience, mobile communication networks have introduced a Network Data Analytics Function (NWDAF) to analyze and process network data, thereby providing decision support for network operators or service providers. Network elements (NEs) in the network can send subscription requests to the NWDAF based on service requirements. The NWDAF receives and stores data from various nodes or devices in the network, such as user data, device data, or network performance data. By analyzing and processing the collected data, it can obtain processing results and return them to the subscribing NE.

[0004] However, the existing calls to one or more data analysis functions rely on the logical functions of the requesting network element itself, requiring professional developers to develop code based on business needs and specific scenarios, design fixed interaction processes and related parameters, etc. The data processing process is not flexible and changeable enough. When applied to scenarios such as different network states or different terminal states, it may cause problems such as waste of network resources or degradation of service quality, and has poor adaptability. Summary of the Invention

[0005] The present application provides a communication method and device for solving the problem that in the call of the existing data analysis function, the fixed interaction process and related parameters may cause network resource waste or service quality degradation when applied to different network states or different terminal states, and the problem of poor adaptability.

[0006] To achieve the above objectives, this application adopts the following technical solutions:

[0007] In a first aspect, a communication method is provided, which can be executed by a first network element or a module (such as a chip or circuit) of the first network element. The method includes: receiving a first message from a second network element, the first message being used to request task decomposition of at least one service request; obtaining a task decomposition result, the task decomposition result including identification information of one or more service functions, wherein the task decomposition result is obtained based on an artificial intelligence (AI) model, and the service function is used to implement a corresponding data processing function; and sending the task decomposition result to the second network element.

[0008] In the above implementation, the first network element can receive a task decomposition request from the second network element, thereby realizing the decomposition of network tasks through interaction between network elements in the wireless communication system. According to different network conditions, the AI ​​model can dynamically obtain different schemes for calling corresponding service functions and indicate the identifier of the service function, so that the second network element can request to subscribe to the service from the indicated service function and realize the corresponding data processing function, thereby improving the flexibility of network task planning, avoiding resource waste caused by redundant calls, and improving communication efficiency.

[0009] In one embodiment, the first message includes first indication information, which includes an identifier of the business type corresponding to the service request, or the first indication information includes identification information of the data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

[0010] In the above implementation, the first message can carry an identifier of the business type to indicate task decomposition for the business type and request feedback of the task decomposition result. In addition, it can also carry an identifier of the data decomposition task to indicate task decomposition or to indicate task decomposition for different business types, thereby improving the flexibility of indicating task decomposition requests and improving communication efficiency.

[0011] In one embodiment, the service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: a target parameter corresponding to the service guarantee, at least one preset threshold corresponding to the service guarantee, or a policy priority corresponding to the service guarantee.

[0012] In the above implementation, the first message can carry the expected indicators of the business corresponding to the service request, so that the obtained task decomposition result meets the expected indicators of the requested business, thereby meeting the business needs of the requester, and achieving the purpose of intelligent task decomposition for scenarios such as different network states or different terminal states, improving the flexibility of network task planning, avoiding resource waste caused by redundant calls, etc., and improving communication efficiency.

[0013] In one embodiment, the target parameter includes at least one of the following information: the number or proportion of terminals corresponding to the service guarantee, the duration corresponding to the service guarantee, and the service quality indicator or parameter corresponding to the service guarantee.

[0014] In the above implementation, for service assurance requirements of different types of services, the first message may carry target parameters corresponding to the service assurance, so that the task decomposition result can meet the requested service expectation indicators and improve the flexibility of network task planning.

[0015] In one embodiment, the preset threshold includes at least one of the following information: a first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

[0016] In the above implementation, the first message can carry a preset threshold corresponding to the service guarantee, such as a duration threshold or a resource threshold, so that the task decomposition result can meet the expected indicators of the service guarantee corresponding to the preset threshold, thereby improving the flexibility and intelligence of network task planning.

[0017] In one embodiment, the policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

[0018] In one embodiment, the method includes: sending a registration request to a third network element, including second indication information for indicating that the first network element supports network task decomposition capability.

[0019] In the above implementation manner, the first network element can indicate to the third network element that it supports the network task decomposition capability during the network element registration phase, so that the third network element can store the capability information of the network element. When other network elements in the network request to query the network element for the task decomposition service, the information of the first network element can be sent to the network element side requesting the query, so that the network elements in the network can request to subscribe to the task decomposition service from the first network element, which can improve the flexibility and intelligence of network task planning and improve communication efficiency.

[0020] In one embodiment, the registration request further includes identification information of the first network element and service information supported by the first network element, where the service information includes a subscription service for network task decomposition and a notification service for task decomposition results.

[0021] In one embodiment, the task decomposition result further includes at least one of the following information: one or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

[0022] In the above implementation, the task decomposition result carries the call time information corresponding to each service function, so that the second network element requesting the task decomposition function can call multiple service functions in sequence according to the task decomposition result, thereby improving the flexibility of network task planning, avoiding resource waste caused by redundant calls, etc., and improving communication efficiency.

[0023] In one embodiment, obtaining the task decomposition result includes: receiving the task decomposition result from the fourth network element. In the above embodiment, the task decomposition process can be implemented by the fourth network element or other network elements. For example, the first network element can receive the task decomposition result of the fourth network element and feed it back to the second network element side that requests the task decomposition service, thereby improving the flexibility of the task decomposition process. It is not limited to being implemented by a specific network element, and can be implemented by collaborative processing or distributed processing by multiple network elements.

[0024] In one embodiment, the AI ​​model includes a pre-trained language model. In the above embodiment, the pre-trained language model can be used to implement the reasoning process of task decomposition and obtain the task decomposition results. This can then be used to apply the strong learning and reasoning capabilities of the pre-trained language model to implement task decomposition planning, improve the flexibility of network task planning, avoid resource waste caused by redundant calls, and improve communication efficiency.

[0025] In one embodiment, obtaining the task decomposition result includes: generating an input prompt word corresponding to a pre-trained language model based on the first indication information and the expected indicator; inputting the input prompt word into the pre-trained language model to obtain the task decomposition result; or, sending the input prompt word to a fifth network element and receiving the task decomposition result from the fifth network element.

[0026] In the above implementation, the first network element and other network elements can collaboratively implement any step in the task decomposition implementation process, such as generating input prompt words, data collection or model reasoning, thereby improving the flexibility of the task decomposition implementation process. It is not limited to a specific network element for implementation, and can be implemented by collaborative processing of multiple network elements or distributed processing.

[0027] In one embodiment, the method further includes: collecting network data, and inputting the collected network data into the pre-trained language model to obtain the task decomposition result.

[0028] In one embodiment, the first network element is a network task decomposition function NPF, or the first network element is a network data analysis function NWDAF.

[0029] In one implementation, the third network element is a network storage function NRF.

[0030] In a second aspect, a communication method is provided, which can be executed by a second network element or by a module (such as a chip or circuit) of the second network element. The method includes: sending a first message to a first network element, the first message being used to request task decomposition of at least one service request; receiving a task decomposition result corresponding to at least one service request from the first network element, the task decomposition result including identification information of one or more service functions, wherein the task decomposition function is obtained based on an artificial intelligence (AI) model, and the service function is used to implement a corresponding data processing function.

[0031] In one embodiment, the method further includes: sending a subscription request to the service function according to identification information of one or more service functions included in the task decomposition result.

[0032] In one embodiment, before sending the first message to the first network element, the method also includes: sending a second message to a third network element, wherein the second message is used to request information about network elements with network task decomposition capabilities; and receiving a response message from the third network element, wherein the response message includes information about at least one candidate network element, and the at least one candidate network element includes the first network element.

[0033] In one embodiment, the first message includes first indication information, which includes an identifier of the business type corresponding to the service request, or the first indication information includes identification information of the data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

[0034] In one embodiment, the service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: a target parameter corresponding to the service guarantee, at least one preset threshold corresponding to the service guarantee, or a policy priority corresponding to the service guarantee.

[0035] In one embodiment, the target parameter includes at least one of the following information: the number or proportion of terminals corresponding to the service guarantee, the duration corresponding to the service guarantee, and the service quality indicator or parameter corresponding to the service guarantee.

[0036] In one embodiment, the preset threshold includes at least one of the following information: a first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

[0037] In one embodiment, the policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

[0038] In one embodiment, the task decomposition result further includes at least one of the following information: one or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

[0039] In one embodiment, the AI ​​model includes a pre-trained language model.

[0040] In a third aspect, a communication method is provided, which can be performed by a third network element or a module (e.g., a chip or circuit) of the third network element. The method includes: receiving a registration request from a first network element, the registration request including second indication information; and confirming, based on the second indication information, that the first network element supports network task decomposition capability.

[0041] In one embodiment, the registration request further includes identification information of the first network element and service information supported by the first network element, where the service information includes a subscription service for network task decomposition and a notification service for network task decomposition results.

[0042] In one embodiment, the method also includes: receiving a second message from a second network element, the second message being used to request information about network elements with network task decomposition capabilities; and sending a response message to the second network element, the response message including information about at least one candidate network element, the at least one candidate network element including the first network element.

[0043] In one embodiment, the first network element is a network task decomposition function NPF, or the first network element is a network data analysis function NWDAF.

[0044] In one implementation, the third network element is a network storage function NRF.

[0045] In a fourth aspect, a communication device is provided for implementing the above method. The communication device may be the first network element in the first aspect, or the second network element in the second aspect, or the third network element in the third aspect, or a node or device including the first network element, the second network element, or the third network element, or a module in the first network element, the second network element, or the third network element, such as a chip, a chip system, or a circuit, or a logical node, logical module, or software that can implement some or all of the functions.

[0046] The communication device includes modules, units, or means corresponding to the above-mentioned method, which can be implemented by hardware, software, or hardware executing corresponding software implementation. The hardware or software includes one or more modules or units corresponding to the above-mentioned functions.

[0047] In conjunction with the fourth aspect above, in one possible implementation, the communication device may include a processing module and a transceiver module. The processing module may be configured to implement the processing functions described in any of the above aspects and any possible implementations thereof. The processing module may, for example, be a processor. The transceiver module, also referred to as a transceiver unit, may be configured to implement the transmitting and / or receiving functions described in any of the above aspects and any possible implementations thereof. The transceiver module may be comprised of a transceiver circuit, a transceiver, a transceiver, or a communication interface.

[0048] In combination with the fourth aspect above, in a possible implementation, the transceiver module includes a sending module and a receiving module, which are respectively used to implement the sending and receiving functions in any of the above aspects and any possible implementations thereof.

[0049] In a fifth aspect, a communication device is provided, comprising: a processor; the processor is configured to be coupled to a memory, and after reading instructions from the memory, execute the method described in any of the above aspects according to the instructions. The communication device may be the first network element described in the first aspect, or the second network element described in the second aspect, or the third network element described in the third aspect, or a node or device including the first network element, the second network element, or the third network element, or a module in the first network element, the second network element, or the third network element, such as a chip, a chip system, or a circuit, or a logical node, logical module, or software that can implement some or all of the functions.

[0050] In combination with the fifth aspect above, in a possible implementation, the communication device further includes a memory, which is used to store necessary program instructions and data.

[0051] In conjunction with the fifth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of a chip or include a chip and other discrete devices.

[0052] In a sixth aspect, a communication device is provided, comprising: a processor and an interface circuit; the interface circuit is configured to receive a computer program or instruction and transmit it to the processor; and the processor is configured to execute the computer program or instruction so that the communication device performs the method described in any of the above aspects. The communication device may be the first network element described in the first aspect, or the second network element described in the second aspect, or the third network element described in the third aspect, or a node or device including the first network element, the second network element, or the third network element, or a module in the first network element, the second network element, or the third network element, such as a chip, a chip system, or a circuit, or a logical node, a logical module, or software that can implement some or all of the functions.

[0053] In conjunction with the sixth aspect above, in one possible implementation, the communication device is a chip or a chip system. Optionally, when the communication device is a chip system, it can be composed of a chip or include a chip and other discrete devices.

[0054] In a seventh aspect, a computer-readable storage medium is provided, wherein instructions are stored in the computer-readable storage medium, and when the computer-readable storage medium is run on the computer, the computer can execute the method described in any one of the above aspects.

[0055] In an eighth aspect, a computer program product comprising instructions is provided, which, when executed on a computer, enables the computer to execute the method described in any one of the above aspects.

[0056] In a ninth aspect, a communication system is provided, which includes a first network element for executing any possible implementation of the first aspect, and a second network element for executing any possible implementation of the second aspect.

[0057] In combination with the above-mentioned ninth aspect, in a possible implementation manner, the communication system also includes a third network element for executing any possible implementation manner of the above-mentioned third aspect.

[0058] Among them, the technical effects brought about by any possible implementation method in the second to ninth aspects can refer to the technical effects brought about by different possible implementation methods in the above-mentioned first aspect, and will not be repeated here.

[0059] It is understandable that, provided that the solutions are not contradictory, the solutions in each aspect can be combined. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] FIG1 is a schematic diagram of the architecture of a communication system provided in an embodiment of the present application;

[0061] FIG2 is a schematic diagram of a data processing service flow provided in an embodiment of the present application;

[0062] FIG3 is a schematic diagram of the architecture of another communication system provided in an embodiment of the present application;

[0063] FIG4 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0064] FIG5 is a flow chart of a communication method provided in an embodiment of the present application;

[0065] FIG6 is a flowchart of a task decomposition process according to an embodiment of the present application;

[0066] FIG7 is a schematic structural diagram of another communication device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0068] It should be noted that, in this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described in this application as "exemplary" or "for example" should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0069] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0070] First, a brief introduction to the implementation environment and application scenarios of the embodiments of the present application is given.

[0071] The communication method provided in the embodiments of the present application can be applied to the service-oriented architecture shown in Figure 1. Figure 1 takes the network service architecture of the fifth generation (5G) mobile communication system as an example to illustrate the interaction between network functions (NFs) and entities and the corresponding interfaces. The 3rd Generation Partnership Project (3GPP) service-based architecture (SBA) of the 5G system mainly includes the following network functions and entities: User Equipment (UE), at least one access network (AN) or radio access network (RAN) node, User Plane Function (UPF), Data Network (DN), Access and Mobility Management Function (AMF), Session Management Function (SMF), Policy Control Function (PCF), Application Function (AF), Unified Data Management (UDM), Network Exposure Function (NEF), Network Data Analytics Function (NWDAF), Unified Data Repository (UDR), Operations, Administration and Management (OAM), namely network management, Binding Support Function (BSF) and Network NF Repository Function (NRF).

[0072] Among them, UE, (R)AN node, UPF and DN are generally referred to as user plane network functions and entities (or user plane network elements), and the other parts are generally referred to as control plane network functions and entities (or control plane network elements). The control plane network element is defined by 3GPP as the processing function in a network. The control plane network element has 3GPP-defined functional behaviors and 3GPP-defined interfaces. NF can be a network element running on dedicated hardware, or a software instance running on dedicated hardware, or a virtual function instantiated on a suitable platform, such as being implemented on a cloud infrastructure.

[0073] The following is a detailed introduction to the main functions of each network element.

[0074] (R)AN Node: The (R)AN can be either an AN or a RAN, and can also be referred to as access network equipment, a RAN entity, or an access node. It forms part of a communication system and helps terminals access the communication network. For example, the (R)AN can be various base stations, such as macro base stations, micro base stations, wireless controllers, relay stations, access points, or network equipment in vehicle-mounted devices, wearable devices, or future public land mobile networks (PLMNs). The (R)AN is primarily responsible for radio resource management, quality of service management, data compression, and encryption on the air interface side.

[0075] In addition, the (R)AN node can also be an access node in an open access network (open RAN, O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system, or an access node in a communication system that integrates two or more of the above systems.

[0076] In one possible scenario, a RAN node may be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next generation NodeB (gNB), a next generation base station in a sixth generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node may be a macro base station, a micro base station or an indoor station, a relay node or a donor node, or a wireless controller in a CRAN scenario. Optionally, a RAN node may also be a server, a wearable device, a vehicle or an onboard device. For example, an access network device in vehicle to everything (V2X) technology may be a road side unit (RSU). All or part of the functions of the RAN node in this application may also be implemented by software functions running on hardware, or by virtualized functions instantiated on a platform (e.g., a cloud platform). The RAN node in this application may also be a logical node, a logical module, or software that can implement all or part of the functions of a RAN node.

[0077] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, and different RAN nodes respectively implement part of the functions of the base station. For example, the RAN 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). The CU and DU can be set separately, or they 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 radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0078] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in the ORAN system, CU may also be called O-CU (Open CU), DU may also be called O-DU, CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. For the convenience of description, this application uses CU, CU-CP, CU-UP, DU and RU as examples for description. Any unit of CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0079] UE: It can also be called terminal, terminal equipment, mobile station, mobile terminal, etc. The terminal can be widely used in various scenarios, such as device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), Internet of Things (IOT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearable, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home device, etc. The embodiments of this application do not limit the device form of the terminal.

[0080] UPF: Responsible for forwarding and receiving user data. The UPF receives downlink data from the DN and transmits it to the UE via the (R)AN. The UPF also receives uplink data from the UE via the (R)AN and forwards it to the DN.

[0081] DN: For example, a DN can be a carrier service network, an Internet access network, or a third-party service network. The DN can exchange information with the UE through PDU sessions. PDU sessions can be of various types, such as Internet Protocol version 4 (IPv4) and IPv6.

[0082] AMF: Mainly responsible for processing control plane messages and user mobility management, including mobility status management, allocating temporary user identities, and authenticating and authorizing users. For example, these functions include access control, mobility management, registration and deregistration, and network element selection.

[0083] SMF: Mainly used for session management, session establishment, UE IP address allocation and management, responsible for session establishment, modification and release, and quality of service (QoS) control.

[0084] PCF: Mainly used to manage policy rules and user subscription information.

[0085] UDM: Mainly used for authentication and credit processing, responsible for managing subscription data, user identification processing, access authorization, registration / mobility management, subscription management, and short message management. For example, when a user's subscription data is modified, the UDM is responsible for notifying the corresponding network element.

[0086] NEF: Mainly used to provide corresponding security guarantees to ensure the security of external applications to the communication network, and provide functions such as external application QoS customization capability exposure, mobility status event subscription, and AF request distribution.

[0087] NRF: Mainly used to provide internal / external addressing functions, etc.

[0088] AF: Mainly used to send application-affected data routing information to the network side, and to perform policy control through interaction between network open function elements and the policy framework.

[0089] NWDAF: It has data collection, training, analysis, or reasoning functions. It can be used to collect relevant data from network elements, third-party service servers, terminals, or network management systems, perform analysis and training based on the relevant data, and feedback data analysis results to network elements or nodes that request to subscribe to the data analysis function.

[0090] Among them, the functions of other network elements included in Figure 1 can be referred to the relevant descriptions in conventional technologies and will not be repeated here.

[0091] It should be noted that the network architecture shown in Figure 1 is for example purposes only and is not intended to limit the technical solutions of this application. Those skilled in the art will appreciate that, in a specific implementation, other network elements or devices may also be included, and the number of access network devices, terminals, and / or core network devices may also be determined based on specific needs.

[0092] Optionally, each network element shown in FIG1 may be a device, a functional module within a device, or a logical functional unit. It is understood that the above functions may be network elements in a hardware device, such as a communication chip in a mobile phone, or software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform).

[0093] In one embodiment, the process of a node in a network requesting a data analysis function to subscribe to a data processing service can be shown in Figure 2. As a consumer of the data analysis service, a node in the network, such as a NF, can send a subscription request to the NWDAF to request the NWDAF to analyze or compute the specified data and feedback the data analysis results to the node NF that requested the subscription.

[0094] As shown in FIG2 , the process of data processing service may include the following steps.

[0095] Step 1: NF sends a subscription request to NWDAF.

[0096] Among them, NF can trigger subscription requests according to its own logic, and different data analysis or processing functions can be distinguished by different identifiers. For example, the subscription request can carry an analytics function ID (Analytics ID) to indicate the requested data analysis function or data processing function, etc.

[0097] For example, a NF can send a message such as Nnwdaf_Analytics Info or Nnwdaf_Analytics Subscription to the NWDAF to subscribe to the data analysis or processing capabilities it requires, and specify the required subscription parameters in the service. Subsequently, the NF can also update or cancel the relevant data analysis subscription to the NWDAF.

[0098] Step 2: NWDAF obtains the corresponding data analysis results based on the subscription request.

[0099] For example, NWDAF can receive and store data from various nodes or devices in the network, such as user data, device data, or network performance data, and analyze and process the collected data according to the subscription request of NF to obtain data analysis results.

[0100] Step 3: NWDAF sends the data analysis results to NF.

[0101] However, in the above-mentioned embodiments, network elements perform data analysis or processing by invoking NWDAF. The processes and related parameters are based on the logic of the NWDAF data analysis function and cannot be directly applied to task planning. Furthermore, the current implementation of NWDAF invocation by NFs is based on scenario-specific code development by professionals. For example, fixed interaction processes and related subscription parameters can be designed for specific services. If an NF wishes to invoke NWDAF to implement a specific service, the invocation logic design is complex. The process for invoking NWDAF services is not flexible enough for different network or terminal states, and is prone to redundant invocations, potentially wasting network resources or degrading service quality. This results in poor adaptability.

[0102] In this application, NWDAF is a functional network element in 5G. For the evolution of 6G or future wireless communication networks, NWDAF can evolve or be replaced by a new functional network element with data analysis or processing capabilities. This application does not limit the name or form of the functional network element.

[0103] In order to solve the above problems, the present application provides a communication method for task decomposition based on an artificial intelligence (AI) model. Optionally, data analysis or processing tasks can be decomposed through a pre-trained language model, and the task decomposition results can be obtained and fed back to the network element that requested the task decomposition task. The network element can then call the data processing function based on the task decomposition result, so that the communication system can adapt to different business scenarios, realize intelligent data processing function call services, meet different implementation scenarios and business needs, and improve communication efficiency.

[0104] Pre-trained language models, also known as large-scale pre-trained language models, are language models trained on large amounts of data and can be used to implement natural language processing (NLP) tasks. Currently, pre-trained language models based on the "pre-training-fine-tuning" paradigm are widely used, such as the chatbot ChatGPT. These models possess powerful human-computer dialogue capabilities, task generalization capabilities, and logical reasoning abilities, enabling them to handle complex data processing tasks.

[0105] Specifically, the value of applying pre-trained language models, such as ChatGPT, to mobile communication networks lies in the following aspects: Pre-trained language models can use contextual learning to understand the distribution of input data, enabling real-time reasoning based on network information, enabling highly autonomous communication networks. Pre-trained language models can achieve multi-scenario generalization through fine-tuning or prompt engineering, helping to reduce the cost of frequent model updates within the network while improving performance robustness to varying scenarios. Compared to traditional models, pre-trained language models can more effectively utilize large amounts of unlabeled network data, reducing labor costs while improving intelligence. The logical reasoning capabilities of pre-trained language models also facilitate the analysis and scheduling of high-level network goals, improving overall resource utilization efficiency. Pre-trained language models can autonomously generate relevant mobile network agents based on goals, autonomously detect and identify network issues, and then autonomously collaborate across multiple network elements and models to resolve problems, enhancing network automation.

[0106] For example, an intelligent agent can be constructed based on a large language model (LLM) to achieve task decomposition, breaking down more complex tasks into smaller, more manageable sub-goals, thereby achieving efficient processing of complex tasks.

[0107] In addition, as shown in FIG3 , a communication system is further provided for an embodiment of the present application, and the communication method provided in the embodiment of the present application can be applied to the communication system shown in FIG3 . The communication system 30 may include a first network element 301 and a second network element 302, wherein the second network element 302 may be used to send a task decomposition request (such as a first message) to the first network element 301, and the first network element 301 may be used to obtain a task decomposition result based on the received task decomposition request using an AI model such as a pre-trained language model system, wherein the task decomposition result includes identification information of one or more data processing functions, and then the task decomposition result may be sent back to the second network element 302.

[0108] Optionally, the second network element 302 may be a NF in the network, such as PCF or OAM.

[0109] Optionally, the first network element 301 may be an NWDAF, or a node in other networks.

[0110] Alternatively, the first network element 301 may optionally include a network planning function (NPF). The NPF has certain logical analysis and planning capabilities and can be used to recommend how other network elements should invoke existing network functions. For example, based on the PCF's subscription request, the NPF can recommend which NWDAF analysis results the PCF can invoke to dynamically adjust the quality of service (QoS) in the network to ensure service objectives.

[0111] Optionally, the communication system 30 may further include a third network element 303, configured to implement function registration and discovery of the first network element 301 in the communication system 30. Optionally, the third network element 303 may specifically be an NRF.

[0112] Optionally, the first network element 301 may be integrated with a pre-trained language model, or the first network element 301 may be a device or system including a pre-trained language model, or the first network element 301 may call the pre-trained language model through other devices or nodes to obtain the task decomposition result. For example, the first network element 301 may obtain the task decomposition result through distributed processing with 304. This application is not limited to this.

[0113] Optionally, the communication system 30 may further include one or more data processing functions for implementing the data processing or analysis tasks requested to be decomposed by the first network element 301. Exemplarily, the data processing function may be implemented by the NWDAF, or by other network elements, and this application does not specifically limit this. For example, the communication system 30 may further include one or more NWDAFs for implementing different data processing or data analysis functions. After the second network element 302 receives the task decomposition result, it may call the corresponding NWDAF to perform data processing tasks or data analysis tasks, etc. according to the one or more data processing functions included in the task decomposition result.

[0114] It is understandable that the devices or network elements in the communication system 30 can communicate directly with each other or communicate through forwarding by other devices. The embodiments of the present application do not specifically limit this.

[0115] It is understood that FIG3 is merely a schematic diagram and does not limit the applicable scenarios of the technical solutions provided in this application. Those skilled in the art should understand that, in a specific implementation, the communication system 30 may include fewer devices or network elements than those shown in FIG3 , or the communication system 30 may also include other devices or other network elements. The number of devices or network elements in the communication system 30 may also be determined based on specific needs.

[0116] It should be noted that the communication system shown in Figure 1 or Figure 3 is for example only and is not intended to limit the technical solution of this application. Those skilled in the art should understand that in a specific implementation, the communication system may also include other devices or network elements, and the number of each network element may also be determined according to specific needs.

[0117] Optionally, each network element in Figure 1 or Figure 3 of the embodiment of the present application can be a functional module within a device. It can be understood that the above-mentioned functions can be network elements in hardware devices, such as communication chips in mobile phones, or software functions running on dedicated hardware, or virtualized functions instantiated on a platform (for example, a cloud platform).

[0118] For example, each network element in Figure 1 or Figure 3 can be implemented by the communication device 400 in Figure 4. Figure 4 shows a hardware structure diagram of a communication device applicable to embodiments of the present application. The communication device 400 includes at least one processor 401, a communication line 402, a memory 403, and at least one communication interface 404.

[0119] The processor 401 may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0120] The communication link 402 may include a path for transmitting information between the above components, such as a bus.

[0121] The communication interface 404 uses any transceiver or other device for communicating with other devices or communication networks, such as an Ethernet interface, a RAN interface, a wireless local area network (WLAN) interface, etc.

[0122] The memory 403 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory can be independent and connected to the processor via a communication line 402. The memory can also be integrated with the processor. The memory provided in the embodiment of the present application can generally have non-volatility. Among them, the memory 403 is used to store the computer execution instructions involved in executing the solution of the present application, and is controlled by the processor 401. The processor 401 is used to execute the computer-executable instructions stored in the memory 403, thereby implementing the method provided in the embodiment of the present application.

[0123] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, which is not specifically limited in the embodiments of the present application.

[0124] In a specific implementation, as an embodiment, the processor 401 may include one or more CPUs, such as CPU0 and CPU1 in FIG. 4 .

[0125] In a specific implementation, as an embodiment, the communication device 400 may include multiple processors, such as the processor 401 and the processor 407 in FIG4 . Each of these processors may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0126] In a specific implementation, as an embodiment, the communication device 400 may further include an output device 405 and an input device 406. The output device 405 communicates with the processor 401 and can display information in a variety of ways. For example, the output device 405 can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device 406 communicates with the processor 401 and can receive user input in a variety of ways. For example, the input device 406 can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0127] The communication device 400 described above can be a general-purpose device or a dedicated device. In a specific implementation, the communication device 400 can be a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal, an embedded device, or a device having a similar structure to that shown in FIG4 . The embodiments of the present application do not limit the type of the communication device 400.

[0128] The communication method provided in the embodiments of the present application is described in detail below.

[0129] It should be noted that the message names between network elements or the names of parameters in the messages in the following embodiments of the present application are only examples, and other names may be used in specific implementations. The embodiments of the present application do not specifically limit this.

[0130] It is understood that some or all of the steps in the embodiments of the present application are merely examples, and the embodiments of the present application may also perform other steps or variations of various steps. In addition, the steps may be performed in a different order than those presented in the embodiments of the present application, and it is possible that not all of the steps in the embodiments of the present application need to be performed.

[0131] As shown in FIG5 , a communication method is provided in an embodiment of the present application, and the method may include the following steps.

[0132] 501: The second network element sends a first message to the first network element.

[0133] The first message is used to request task decomposition of at least one service request. The service request can be a request related to user services, such as a service request related to the application side's needs on the network side, such as a service request in a live broadcast service. This application does not limit the specific type of service request.

[0134] In one embodiment, the service request includes at least one expected indicator corresponding to a business. For example, the first message is used to indicate the expected indicator corresponding to one or more businesses, that is, the first message is used to request task decomposition of at least one business based on the expected indicator. For example, the first message may be a task decomposition request, which is used to request task decomposition of the first business. The first message may include the expected indicator corresponding to the first business, so that the task decomposition of the first business can achieve the expected indicator and feedback the task decomposition result. For another example, the first message may be a subscription message, which is used to request subscription to the result of task decomposition of a specific business, so that the task decomposition can achieve the expected indicator.

[0135] The expected indicator may include specific parameters or may include a natural language description of the requirement, etc., which is not limited in this application. For example, if the expected indicator included in the first message is a natural language description of the requirement, then when the pre-trained language model is used for processing, the pre-trained language model can process the natural language description of the requirement in the first message.

[0136] In one implementation, the first network element may be a network task decomposition function NPF, or a NWDAF or other network element or node.

[0137] In one embodiment, the second network element may be an NF in the communication network or other network elements or nodes in the core network. As a consumer of the task decomposition function, the second network element may send a first message to the first network element, requesting the execution of a specific task decomposition function, and feedback the corresponding task decomposition result, so that the first network element can call different data processing functions according to the task decomposition result to execute a specific business or implement a service.

[0138] In one embodiment, the first message may include an indication of the service type. For example, different service types correspond to different identification information. For example, the first message may include first indication information for indicating the identification information corresponding to the service type. Exemplary service types may include live broadcast service, game acceleration service, or high-definition video service, etc., which can be distinguished by different identifications.

[0139] In one embodiment, the expected indicator corresponding to the service may include at least one of the following information: a target parameter corresponding to the service guarantee, at least one preset threshold corresponding to the service guarantee, or a policy priority corresponding to the service guarantee.

[0140] The target parameter corresponding to the service guarantee may refer to the target parameter to be optimized corresponding to the expected indicator to be achieved for the requested service. Specifically, the target parameter corresponding to the service guarantee may include one or more parameters.

[0141] Optionally, the target parameter corresponding to the service guarantee may include at least one of the following information: the number or proportion of terminals corresponding to the service guarantee, the duration corresponding to the service guarantee, or a service quality indicator or parameter corresponding to the service guarantee.

[0142] For example, for a live broadcast service, the target parameters corresponding to service assurance may include:

[0143] 1. Number or proportion of terminals corresponding to service assurance: that is, the number of terminals required for the live broadcast service, or the proportion of terminals that need to be guaranteed in the terminal group of the live broadcast service;

[0144] 2. Duration of service guarantee: This refers to the duration of the live broadcast service that needs to be guaranteed. The unit can be minutes, hours, days or other duration units.

[0145] 3. Service quality indicators or parameters corresponding to business assurance: that is, the quality indicators or required parameters required to provide the live broadcast business. For example, the software quality metric (MOS) score corresponding to the live broadcast business must be greater than or equal to 4.

[0146] In addition, at least one preset threshold corresponding to the business guarantee refers to the specific limit value corresponding to the data processing task that needs to be met by the task decomposition request of the first message, for example, the limit value of the data processing time (time threshold), or the limit value of the data processing resources (resource threshold).

[0147] In one embodiment, the preset threshold includes at least one of the following information: a first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling at least one service function, or a third threshold corresponding to the energy consumption of calling at least one service function.

[0148] Exemplarily, the first message sent by the second network element to the first network element is used to request the first network element to obtain the task decomposition result, which is used to indicate the call of one or more service functions to implement the business requested by the first message and to ensure the expected indicators corresponding to the business. Based on this, the first message may include a first threshold value for indicating the total call duration requirement for all service functions required to be called for the business. For another example, the first message may include a second threshold value for indicating the number requirement for all service functions required to be called for the business. For another example, the first message may include a third threshold value for indicating the energy consumption requirement corresponding to all service functions required to be called for the business.

[0149] In addition, based on the aforementioned expected indicators, when the duration threshold and resource threshold corresponding to the task decomposition request are met, or when both the duration threshold and the resource threshold are difficult to meet, the expected indicators can also include the policy priority corresponding to the service guarantee, that is, the first network element can indicate which indicator or threshold to prioritize when determining the task decomposition result based on the expected indicators.

[0150] For example, the policy priority may include a first policy or a second policy, wherein the first policy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the sum of the data processing time is higher, and the sum of the data processing time should be given priority and guaranteed. For example, when the duration threshold and the resource threshold are restricted at the same time, the output result with the lowest total duration can be determined as the task decomposition result according to the first policy. The second policy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of data processing functions and / or processing energy consumption is higher, and the number of service functions and / or processing energy consumption should be given priority and guaranteed. For example, when the duration threshold and the resource threshold are restricted at the same time, the output result with the lowest number of service functions and / or processing energy consumption can be determined as the task decomposition result according to the second policy.

[0151] Exemplarily, the first message sent by the second network element to the first network element may include subscription parameters shown in Table 1 below.

[0152] Table 1. Expected business indicators

[0153] In one embodiment, before the second network element sends the first message to the first network element, the first network element may register its function with a third network element (such as a network storage function), so that other network elements or nodes in the communication network (such as the second network element) can request the third network element to query and obtain network elements or nodes that can implement the task decomposition function, such as the first network element, according to business needs. Subsequently, other network elements or nodes can send subscription requests corresponding to task decomposition (such as the first message) to the first network element according to business needs.

[0154] Optionally, the process of the first network element performing function registration and the process of the second network element discovering the first network element may include the following steps 500 - 1 to 500 - 3 .

[0155] 500-1: The first network element sends a registration request to the third network element.

[0156] The registration request may include second indication information for indicating that the first network element supports network task decomposition capability. Exemplarily, the second indication information may be a planning capability tag, or a network task decomposition capability tag, for indicating the capability of the first network element to support task decomposition.

[0157] In one implementation, the third network element may be an NRF.

[0158] For example, taking the first network element as NPF and the third network element as NRF as an example, NPF can assist other network elements in discovering the first network element by sending a registration request to NRF, and can be used to perform related network task decomposition functions.

[0159] In one embodiment, the registration request may include identification information of the first network element and service information supported by the first network element. The service information may specifically include a subscription service for network task decomposition and a notification service for task decomposition results.

[0160] 500-2: The second network element sends a second message to the third network element.

[0161] The second message may specifically be a query request, which is used to request information of network elements having the network task decomposition capability.

[0162] The second network element may send a query request to the first network element according to its own needs, so as to request to find a network element that meets the conditions.

[0163] The query request may include the function or capability of the network element that the second network element requests to discover. For example, if the second network element needs to find a network element with network task decomposition capability, the query request sent by the second network element to the third network element may include information indicating the network task decomposition capability, for example, the aforementioned second indication information, such as specifically including a planning capability tag, which is used to indicate that the second network element requests to discover a network element with a planning capability tag.

[0164] 500-3: The third network element sends a response message to the second network element.

[0165] Correspondingly, the third network element receives the second message from the second network element.

[0166] Based on the second message, the third network element searches for locally stored information and returns a response message to the second network element. The response message includes information about at least one candidate network element. A candidate network element refers to a network element that meets the query conditions of the second network element. For example, the at least one candidate network element may include the first network element. The information about the candidate network element can be indicated by a network element identifier for the second network element to select and trigger subsequent processes. For example, if the second network element is a NF and the third network element is an NRF, the NF sends a query request to the NRF, which carries the second indication information. After performing a local query, the NRF returns a response message to the NF, which carries the identifier of the NPF.

[0167] 502: The first network element obtains a task decomposition result, including identification information of one or more service functions.

[0168] The task decomposition result may be obtained based on an AI model, such as a pre-trained language model. The task decomposition result may include identifiers of one or more service functions, such as an Analytics ID(s) for a data processing function, which indicates the ID of a data processing function to be invoked by the second network element. The service function may be used to implement the corresponding data processing function.

[0169] In one embodiment, the task decomposition result further includes at least one of the following information: one or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

[0170] For example, the service function may include a data processing function, and the task decomposition result may also include the following information:

[0171] Data processing function identifiers (List of Analytics IDs): For example, when broken down by live broadcast services, this function can recommend that consumers call the Analytics IDs for Service Experience, DN performance, and Network performance deployed in the network. For example, calling Service Experience can analyze future changes in service quality indicators, while analyzing Network performance can reveal changes on the air interface side.

[0172] Subscription Parameters List Per ID: Recommended subscription parameters for each Analytics ID, such as setting standard subscription parameters for the Service Experience ID, such as the time when analytics is needed and the preferred accuracy.

[0173] Usage of Output: This parameter specifies the output usage for each ID, i.e., the threshold range. For example, a network performance prediction metric between 90 and 100 is useful, but values ​​outside this range are not considered.

[0174] The call time information corresponding to each data processing function (Time Stamp of Subscription List Per Analytics ID): indicates which Analytics ID was called at which time.

[0175] Optionally, the first network element may be integrated with an AI model, and the first network element performs relevant processing of task decomposition based on the first message through an AI model such as a pre-trained language model to obtain a corresponding task decomposition result. Alternatively, the first network element may obtain the task decomposition result from other devices, such as a device or system including an AI model such as a pre-trained language model. Alternatively, the first network element may perform distributed processing with other devices to obtain the task decomposition result. This application does not limit the specific implementation method, and several different implementation methods will be exemplarily described below.

[0176] 503: The first network element sends the task decomposition result to the second network element.

[0177] The task decomposition result can be used by the second network element to request a subscription service from the corresponding service function based on the identification information of the service function included in the task decomposition result to obtain the corresponding service. For example, if the service function is a data processing function, the data processing result can be obtained through subscription.

[0178] Optionally, the method further includes the following steps.

[0179] 504: The second network element sends a subscription request to at least one service function.

[0180] Specifically, the second network element may send a subscription request to the corresponding service function according to the identification information of one or more service functions included in the task decomposition result.

[0181] Further optionally, the second network element calls the multiple service functions in sequence according to the corresponding calling time information of the multiple service functions included in the task decomposition result.

[0182] In the above-mentioned implementation mode of the present application, the first network element can dynamically obtain different solutions for calling corresponding service functions according to different network conditions through the business requirements such as expected indicators provided by the second network element. For example, the scheme may include the called service function ID, the calling parameters corresponding to each service function, the output usage method and calling time, etc., thereby improving the flexibility of network task planning, avoiding resource waste caused by redundant calls, etc., and improving communication efficiency.

[0183] In one embodiment, the first indication information in the first message may include identification information corresponding to the business type, or the first indication information may include identification information of the data decomposition task, such as an identification corresponding to the data decomposition task or an identification corresponding to the task type. Different business types may correspond to different identification information of the data decomposition task, or different task types may correspond to different identification information of the data decomposition task.

[0184] Exemplarily, the first network element may be an NPF, and the first message may carry a service type ID, such as a live service ID, to instruct the NF to request task decomposition of the live service.

[0185] In another example, the first network element may be a special NWDAF. The first message may carry a task type identifier to indicate that the NF is requesting a data decomposition task, rather than other data processing tasks. For example, the task type is a decomposition task, or a planning task, and the corresponding Analytics ID (task decomposition) = ID0, indicating that task decomposition is to be performed. The NF may carry the Analytics ID to directly request the NWDAF to subscribe to the task decomposition service function, while providing the corresponding parameters to complete the task decomposition function.

[0186] In another example, the first network element may be an NPF or NWDAF, which can be used to implement task decomposition for multiple service types. The first indication information carried in the first message may be an identifier of the data decomposition task corresponding to the different service types. For each service, a task decomposition ID may be defined separately, so that the service type does not need to be distinguished in the subscription request (such as the first message). For example, for the data decomposition task corresponding to the live broadcast service, Analytics ID1 = "Task decomposition of live broadcast service"; for the data decomposition task corresponding to the gaming service, Analytics ID2 = "Task decomposition of gaming service", which is used to call the task decomposition function corresponding to different services.

[0187] In one embodiment, the first network element may obtain the task decomposition result from another device. For example, the first network element may receive the task decomposition result from a fourth network element. Exemplarily, the fourth network element may be a device including an AI model, such as a pre-trained language model, or the fourth network element may be a device in an AI model system configured to output the output result of the AI ​​model.

[0188] In one embodiment, as shown in Example 1 of FIG6 , in which the first network element includes a pre-trained language model, a specific process of obtaining a task decomposition result through the pre-trained language model may include the following steps:

[0189] Step 1: The first network element generates an input prompt word corresponding to the pre-trained language model.

[0190] According to the above introduction to the pre-trained language model, the pre-trained language model can process natural language. The first network element can generate input prompt words corresponding to the pre-trained language model based on the expected indicators corresponding to the requested service, that is, the parameters related to the network task decomposition carried in the first message are integrated into the input prompt words of the pre-trained language model, and prompt words related to task decomposition are added, such as "decompose into multiple steps", "plan step by step", etc., so that they can be input into the pre-trained language model for task decomposition.

[0191] Step 2: The first network element performs model inference based on the input prompt word through the pre-trained language model to obtain the task decomposition result.

[0192] Optionally, the first network element can also perform data collection. That is, the first network element can determine whether to collect additional information for auxiliary processing based on the requirements of task decomposition. If data collection is determined, the first network element can invoke a data collection process to complete the data collection. For example, the first network element can collect energy consumption information through OAM.

[0193] Specifically, the first network element may perform model inference based on the constructed input prompt words, the collected data, and the pre-trained model to obtain a network task decomposition result.

[0194] Alternatively, in one embodiment, the first network element can perform distributed processing with other devices to obtain task decomposition results. For example, the first network element can be used to generate input prompt words corresponding to the pre-trained language model, and the fifth network element is used to input the input prompt words into the pre-trained language model to obtain task decomposition results.

[0195] For example, as shown in Example 2 of FIG6 , taking the first network element as NPF1 and the fifth network element as NPF2 as an example, obtaining the task decomposition result may include the following steps:

[0196] Step 1: NPF1 generates the input prompt words corresponding to the pre-trained language model.

[0197] Step 2: NPF1 sends the input prompt word to NPF2.

[0198] Step 3: NPF2 performs model inference based on the input prompt word through the pre-trained language model, obtains the task decomposition result, and sends it to NPF1.

[0199] Optionally, the task decomposition process may further include data collection, wherein the data collection may be performed by NPF1, or NPF2, or other network elements such as NPF3.

[0200] In the above implementation, when the NPF performs task decomposition processing, it is not limited to a single network element implementing this function. Based on the actual data processing task, different network elements can be determined to respectively perform one or more steps of generating input prompt words, collecting data, and model inference. This application does not specifically limit the execution order or implementation subject. Distributed task decomposition by multiple network elements can improve the flexibility of task decomposition processing and improve the utilization of network resources.

[0201] The various embodiments mentioned above in this application can be combined without limitation if there is no contradiction between the solutions.

[0202] The above mainly introduces the solution provided by this application from the perspective of interaction between various network elements. Accordingly, this application also provides a communication device, which can be the first network element in the above method embodiment, or a node or device that includes the above task decomposition function, or a component that can be used for the first network element; or, the communication device can be the second network element in the above method embodiment, or a node or device that includes the request task decomposition function, or a component that can be used for the second network element.

[0203] It is understandable that, in order to implement the above functions, the above communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should easily realize that, in combination with the units and algorithmic operations of the various examples described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0204] It should be understood that the above description only uses the first device or data statistics function as an example to describe the interaction between various network elements. In fact, the processing performed by the above first network element is not limited to being performed by only a single network element, and the processing performed by the above second network element is not limited to being performed by only a single network element.

[0205] The present application can divide the functional modules of the communication device according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated modules can be implemented in the form of hardware or software functional modules. It is understood that the division of modules in this application is schematic and is only a logical functional division. In actual implementation, other division methods may be used.

[0206] For example, in the case of dividing the functional modules in an integrated manner, FIG7 shows a schematic structural diagram of a communication device 700. The communication device 700 includes an interface module 701 and a processing module 702.

[0207] In some embodiments, the communication device 700 may further include a storage module (not shown in FIG. 7 ) for storing program instructions and data.

[0208] Exemplarily, the communication device 700 may be used to implement the function of a first network element. The communication device 700 is, for example, the first network element described in the aforementioned embodiments.

[0209] The interface module 701 may be configured to receive a first message from a second network element, where the first message is used to request task decomposition for at least one service request.

[0210] The processing module 702 can be used to obtain the task decomposition result corresponding to the service request, and the task decomposition result includes identification information of one or more service functions, wherein the task decomposition result is obtained based on the artificial intelligence AI model, and the service function is used to implement the corresponding data processing function.

[0211] The interface module 701 may also be configured to send the task decomposition result to the second network element, so that the second network element can request a subscription service based on identification information of the service function included in the task decomposition result.

[0212] In one embodiment, the first message includes first indication information, the first indication information includes an identifier of the business type corresponding to the service request, or the first indication information includes identification information of the data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

[0213] In one embodiment, the service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: a target parameter corresponding to the service guarantee, at least one preset threshold corresponding to the service guarantee, or a policy priority corresponding to the service guarantee.

[0214] In one embodiment, the target parameter includes at least one of the following information: the number or proportion of terminals corresponding to the service guarantee, the duration corresponding to the service guarantee, and the service quality indicator or parameter corresponding to the service guarantee.

[0215] In one embodiment, the preset threshold includes at least one of the following information: a first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

[0216] In one embodiment, the policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

[0217] In one implementation, the interface module 701 may also be configured to send a registration request to a third network element, including second indication information for indicating that the first network element supports the network task decomposition capability.

[0218] In one embodiment, the registration request further includes identification information of the first network element and service information supported by the first network element, where the service information includes a subscription service for network task decomposition and a notification service for task decomposition results.

[0219] In one embodiment, the task decomposition result further includes at least one of the following information: one or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

[0220] In one implementation, the processing module 702 is configured to receive a task decomposition result from the fourth network element.

[0221] In one embodiment, the AI ​​model includes a pre-trained language model.

[0222] In one embodiment, the processing module 702 is used to generate an input prompt word corresponding to the pre-trained language model based on the first indication information and the expected indicator; input the input prompt word into the pre-trained language model to obtain the task decomposition result; or, the interface module 701 can also be used to send the input prompt word to the fifth network element and receive the task decomposition result from the fifth network element.

[0223] In one embodiment, the processing module 702 may also be used to collect network data, and input the collected network data into a pre-trained language model to obtain a task decomposition result.

[0224] In one implementation, the first network element is a network task decomposition function NPF, or the first network element is a network data analysis function NWDAF.

[0225] In one implementation, the third network element is a network storage function NRF.

[0226] In addition, the communication device 700 can also be used to implement the steps performed by the second network element in the embodiment shown above, for example.

[0227] The interface module 701 may be configured to send a first message to the first network element, where the first message is used to request task decomposition of at least one service request.

[0228] The interface module 701 can also be used to receive a task decomposition result corresponding to a service request from the first network element, wherein the task decomposition result includes identification information of one or more service functions, wherein the task decomposition function is obtained based on an artificial intelligence AI model, and the service function is used to implement the corresponding data processing function.

[0229] In one embodiment, the processing module 702 is configured to send a subscription request to the service function according to identification information of one or more service functions included in the task decomposition result.

[0230] In one embodiment, before sending the first message to the first network element, the interface module 701 can also be used to send a second message to the third network element, where the second message is used to request information about network elements with network task decomposition capabilities; and receive a response message from the third network element, where the response message includes information about at least one candidate network element, and the at least one candidate network element includes the first network element.

[0231] In one embodiment, the first message includes first indication information, the first indication information includes an identifier of the business type corresponding to the service request, or the first indication information includes identification information of the data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

[0232] In one embodiment, the service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: a target parameter corresponding to the service guarantee, at least one preset threshold corresponding to the service guarantee, or a policy priority corresponding to the service guarantee.

[0233] In one embodiment, the target parameter includes at least one of the following information: the number or proportion of terminals corresponding to the service guarantee, the duration corresponding to the service guarantee, and the service quality indicator or parameter corresponding to the service guarantee.

[0234] In one embodiment, the preset threshold includes at least one of the following information: a first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

[0235] In one embodiment, the policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

[0236] In one embodiment, the task decomposition result further includes at least one of the following information: one or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

[0237] In one embodiment, the AI ​​model includes a pre-trained language model.

[0238] In addition, the communication device 700 can also be used to implement the steps performed by the third network element in the embodiment shown above, for example.

[0239] The interface module 701 may be configured to receive a registration request from a first network element, where the registration request includes second indication information.

[0240] The processing module 702 may be configured to determine, based on the second indication information, whether the first network element supports the network task decomposition capability.

[0241] In one embodiment, the registration request further includes identification information of the first network element and service information supported by the first network element, where the service information includes a subscription service for network task decomposition and a notification service for network task decomposition results.

[0242] In one embodiment, the interface module 701 can also be used to receive a second message from a second network element, where the second message is used to request information about network elements with network task decomposition capabilities; and send a response message to the second network element, where the response message includes information about at least one candidate network element, and the at least one candidate network element includes the first network element.

[0243] In one embodiment, the first network element is a network task decomposition function NPF, or the first network element is a network data analysis function NWDAF.

[0244] In one implementation, the third network element is a network storage function NRF.

[0245] In summary, when the communication device 700 is used to implement the functions performed by the first network element, the second network element or the third network element in the above embodiments, for other functions that the communication device 700 can implement, please refer to the relevant introduction of any of the above-mentioned embodiments, and no further details will be given.

[0246] In a simple embodiment, those skilled in the art may appreciate that the communication device 700 may be in the form shown in Figure 4. For example, the processor 401 in Figure 4 may call computer-executable instructions stored in the memory 403 to enable the communication device 400 to execute the method described in the above method embodiment.

[0247] Exemplarily, the functions / implementation processes of the processing module 702 in FIG. 7 may be implemented by the processor 401 in FIG. 4 .

[0248] Exemplarily, the function / implementation process of the interface module 701 in FIG. 7 may be implemented through the communication interface 404 in FIG. 4 .

[0249] It is understandable that one or more of the above modules or units can be implemented by software, hardware or a combination of the two. When any of the above modules or units is implemented by software, the software exists in the form of computer program instructions and is stored in a memory, and a processor can be used to execute the program instructions and implement the above method flow. The processor can be built into an SoC (system on chip) or an ASIC, or it can be an independent semiconductor chip. In addition to the core used to execute software instructions to perform calculations or processing within the processor, it can further include necessary hardware accelerators, such as field programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0250] When the above modules or units are implemented in hardware, the hardware can be any one or any combination of a CPU, a microprocessor, a digital signal processing (DSP) chip, a microcontroller unit (MCU), an artificial intelligence processor, an ASIC, a SoC, an FPGA, a PLD, a dedicated digital circuit, a hardware accelerator or a non-integrated discrete device, which can run the necessary software or not rely on the software to execute the above method flow.

[0251] Optionally, the present application also provides a chip system, comprising: at least one processor and an interface, wherein the at least one processor is coupled to a memory via the interface, and when the at least one processor executes a computer program or instruction in the memory, the method in any of the above method embodiments is executed. In one possible implementation, the chip system also includes a memory. Optionally, the chip system can be composed of a chip, or can include a chip and other discrete devices, which is not specifically limited in this application.

[0252] Optionally, the present application also provides a computer-readable storage medium. All or part of the processes in the above-mentioned method embodiments can be completed by a computer program to instruct the relevant hardware. The program can be stored in the above-mentioned computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned method embodiments. The computer-readable storage medium can be an internal storage unit of the communication device of any of the above-mentioned embodiments, such as a hard disk or memory of the communication device. The above-mentioned computer-readable storage medium can also be an external storage device of the above-mentioned communication device, such as a plug-in hard disk, a smart memory card (smart media card, SMC), a secure digital (secure digital, SD) card, a flash card (flash card), etc. equipped on the above-mentioned communication device. Furthermore, the above-mentioned computer-readable storage medium can also include both the internal storage unit of the above-mentioned communication device and an external storage device. The above-mentioned computer-readable storage medium is used to store the above-mentioned computer program and other programs and data required by the above-mentioned communication device. The above-mentioned computer-readable storage medium can also be used to temporarily store data that has been output or is to be output.

[0253] Optionally, the present application also provides a computer program product. All or part of the processes in the above method embodiments may be completed by a computer program instructing related hardware. The program may be stored in the above computer program product, and when executed, the program may include the processes in the above method embodiments.

[0254] Optionally, the present application also provides a computer instruction. All or part of the process in the above method embodiment can be completed by the computer instruction to instruct the relevant hardware (such as a computer, processor, network device or terminal, etc.). The program can be stored in the above computer-readable storage medium or in the above computer program product.

[0255] Optionally, the present application also provides a communication system, including: the first network element and the second network element in the above embodiment.

[0256] Optionally, the communication system may further include the third network element in the above embodiment.

[0257] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0258] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0259] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0260] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0261] The above is only a specific embodiment of the present application, but the scope of protection of this application is not limited to this. Any changes or substitutions within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A communication method, characterized in that: Applied to a first network element, the method includes: receiving a first message from a second network element, wherein the first message is used to request task decomposition of at least one service request; Obtaining a task decomposition result corresponding to the at least one service request, the task decomposition result including identification information of one or more service functions, wherein the task decomposition result is obtained according to an artificial intelligence (AI) model, and the service function is used to implement a corresponding data processing function; Send the task decomposition result to the second network element.

2. The method according to claim 1, characterized in that The first message includes first indication information, and the first indication information includes an identifier of a business type corresponding to the service request, or the first indication information includes identification information of a data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

3. The method according to claim 1 or 2, characterized in that: The service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: A target parameter corresponding to the service assurance, at least one preset threshold corresponding to the service assurance, or a policy priority corresponding to the service assurance.

4. The method according to claim 3, characterized in that The target parameter includes at least one of the following information: The number or proportion of terminals corresponding to business guarantee, the duration corresponding to business guarantee, and the service quality indicators or parameters corresponding to business guarantee.

5. The method according to claim 3 or 4, characterized in that: The preset threshold includes at least one of the following information: A first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

6. The method according to any one of claims 3 to 5, characterized in that: The policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

7. The method according to any one of claims 1 to 6, characterized in that: The method comprises: A registration request is sent to a third network element, including second indication information, used to indicate that the first network element supports network task decomposition capability.

8. The method according to claim 7, characterized in that The registration request also includes identification information of the first network element and service information supported by the first network element, wherein the service information includes a subscription service for network task decomposition and a notification service for task decomposition results.

9. The method according to any one of claims 1 to 8, characterized in that: The task decomposition result also includes at least one of the following information: One or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

10. The method according to any one of claims 1 to 9, characterized in that: The obtaining of the task decomposition result includes: Receive the task decomposition result from the fourth network element.

11. The method according to any one of claims 1 to 9, characterized in that: The AI ​​model includes a pre-trained language model.

12. The method according to claim 11, characterized in that The obtaining of the task decomposition result includes: Generate an input prompt word corresponding to the pre-trained language model according to the first indication information and the expected indicator; The input prompt word is input into the pre-trained language model to obtain the task decomposition result; or, the input prompt word is sent to the fifth network element to receive the task decomposition result from the fifth network element.

13. The method according to claim 10 or 12, characterized in that: The method further comprises: Collect network data, and input the collected network data into the pre-trained language model to obtain the task decomposition result.

14. The method according to any one of claims 1 to 13, characterized in that: The first network element is a network task decomposition function NPF, or the first network element is a network data analysis function NWDAF.

15. The method according to claim 7 or 8, characterized in that The third network element is a network storage function NRF.

16. A communication method, characterized in that: Applied to a second network element, the method comprises: Sending a first message to a first network element, where the first message is used to request task decomposition of at least one service request; Receive a task decomposition result corresponding to the at least one service request from the first network element, the task decomposition result including identification information of one or more service functions, wherein the task decomposition function is obtained according to an artificial intelligence AI model, and the service function is used to implement a corresponding data processing function.

17. The method according to claim 16, characterized in that The method further comprises: According to identification information of one or more service functions included in the task decomposition result, a subscription request is sent to the service function.

18. The method according to claim 16 or 17, characterized in that Before sending the first message to the first network element, the method further includes: Sending a second message to a third network element, where the second message is used to request information of a network element having a network task decomposition capability; A response message is received from a third network element, where the response message includes information of at least one candidate network element, where the at least one candidate network element includes the first network element.

19. The method according to any one of claims 16 to 18, characterized in that: The first message includes first indication information, and the first indication information includes an identifier of a business type corresponding to the service request, or the first indication information includes identification information of a data decomposition task, wherein different business types correspond to different identifiers of data decomposition tasks, or different task types correspond to different identifiers of data decomposition tasks.

20. The method according to any one of claims 16 to 19, characterized in that: The service request includes at least one expected indicator corresponding to the service, and the expected indicator includes at least one of the following information: A target parameter corresponding to the service assurance, at least one preset threshold corresponding to the service assurance, or a policy priority corresponding to the service assurance.

21. The method according to claim 20, characterized in that The target parameter includes at least one of the following information: The number or proportion of terminals corresponding to business guarantee, the duration corresponding to business guarantee, and the service quality indicators or parameters corresponding to business guarantee.

22. The method according to claim 20 or 21, characterized in that The preset threshold includes at least one of the following information: A first threshold corresponding to the total processing time corresponding to calling at least one service function for data processing, a second threshold corresponding to the number of calling the at least one service function, or a third threshold corresponding to the energy consumption of calling the at least one service function.

23. The method according to any one of claims 20 to 22, characterized in that: The policy priority includes a first strategy or a second strategy, wherein the first strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the total processing time is higher; the second strategy is used to indicate that when the task decomposition result is determined according to the expected indicator, the priority corresponding to the number of service functions and / or processing energy consumption is higher.

24. The method according to any one of claims 16 to 23, characterized in that: The task decomposition result also includes at least one of the following information: One or more subscription parameters corresponding to each service function, a range corresponding to at least one parameter output by the service function, or call time information corresponding to each service function.

25. The method according to any one of claims 16 to 24, characterized in that: The AI ​​model includes a pre-trained language model.

26. A communication device, characterized in that: The communication device is used to implement the method according to any one of claims 1-15 or 16-25.

27. A communication device, characterized in that: include: A processor, wherein the processor is coupled to a memory, wherein the memory is used to store programs or instructions, and when the programs or instructions are executed by the processor, the method according to any one of claims 1 to 25 is executed.

28. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instructions are executed, the method according to any one of claims 1 to 25 is performed.

29. A computer program product, comprising computer program code, characterized in that: When the computer program code is run on a computer, the method according to any one of claims 1 to 25 is executed.

30. A communication system, characterized in that: The communication system comprises the first device in the method according to any one of claims 1-15, and the second device in the method according to any one of claims 16-25.

Images