Communication method and apparatus

Abstract

The present application belongs to the technical field of communications, and provides a communication method and apparatus, so as to improve communication efficiency. The method comprises: a first agent network element acquires communication task information, the communication task information being used for declaring a communication task objective to be achieved; and executes an operation corresponding to the communication task objective to obtain an execution result, the operation corresponding to the communication task objective being determined on the basis of the communication task information. An agent network element can process information declaring an objective to obtain an operation required for achieving the objective. Therefore, during communication between agent network elements, an agent network element only needs to declare, in communication task information, a communication task objective to be achieved, and does not need to pay attention to how the network element of the other party specifically carries out implementation, so that signaling interaction can omit indications of specific services and operations, thereby improving the interfacing efficiency of network elements in a communication network, that is, improving the communication efficiency.

Description

Communication methods and devices

[0001] This application claims priority to Chinese Patent Application No. 202411854033.2, filed on December 13, 2024, entitled "Communication Method and Apparatus", the entire contents of which are incorporated herein by reference. Technical Field

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

[0003] With the rapid development of large-scale model technologies, such as ChatGPT (chat generative pre-trained transformer), the integration of mobile communication technology and artificial intelligence (AI) will be further promoted, enabling intelligent and inclusive mobile communication technology and allowing more people to enjoy the convenience brought by intelligent services. The integration of mobile communication technology and AI is likely to manifest more in the fusion of mobile communication systems and large-scale model technologies. A large number of intelligent agents based on large models can be deployed in mobile communication systems, and these agents interact with each other to implement services within the mobile communication system. However, communication between network elements in existing communication networks requires relatively complex operations, making it unsuitable for communication between intelligent agents. Summary of the Invention

[0004] This application provides a communication method and apparatus to simplify the communication mechanism between intelligent agent network elements and improve communication efficiency.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] Firstly, a communication method is provided. This method can be executed by a first intelligent agent network element, or by a component of the first intelligent agent network element, such as a processor, chip, or chip system of the first intelligent agent network element, or by a logic module or software capable of implementing all or part of the first intelligent agent network element. The method includes:

[0007] The system acquires communication task information, executes the operations corresponding to the communication task objectives, and obtains the execution results. The communication task information is used to declare the communication task objectives to be achieved; the operations corresponding to the communication task objectives are determined based on the communication task information; the first and second intelligent agent network elements are network elements in the communication network.

[0008] Intelligent agent network elements can process the information of declared goals to obtain the operations required to achieve the goals. Therefore, when intelligent agent network elements communicate with each other, the intelligent agent network elements only need to declare the communication task goals to be achieved in the communication task information, without needing to care about how the other network element implements them. The signaling interaction can omit the instructions of specific services and operations, thereby improving the docking efficiency of each network element in the communication network, that is, improving communication efficiency.

[0009] In one possible design, obtaining communication task information includes: receiving communication task information from a second intelligent agent network element through a first communication interface, wherein the first communication interface is an interface for receiving communication task information that declares the communication task objective.

[0010] By defining a declarative communication interface, intelligent agent network elements can receive communication task information declaring the communication task target through this interface, thereby enabling efficient communication between intelligent agent network elements. It is understood that the first communication interface can also be an interface used to send communication task information declaring the communication task target from the first intelligent agent network element; or, the first intelligent agent network element can be configured with an interface for sending communication task information declaring the communication task target.

[0011] In one possible design, the operation corresponding to the communication task objective is performed, including: performing the operation corresponding to the communication task objective based on an artificial intelligence (AI) / machine learning (ML) model.

[0012] Optionally, based on the AI / ML model, the operation corresponding to the communication task objective is executed, including: processing the communication task information based on the AI / ML model to obtain the operation corresponding to the communication task objective; and executing the operation corresponding to the communication task objective.

[0013] AI / ML models have powerful data processing and analysis capabilities, so they can flexibly process communication task information to obtain relatively reliable operations corresponding to the communication task objectives, and then execute the corresponding operations to better support the realization of communication between intelligent agent network elements by simply declaring the communication task objectives to be achieved.

[0014] In one possible design, the communication task information is unstructured or semi-structured data.

[0015] Optionally, communication task information being unstructured data includes information constructed using a self-declared language; or, communication task information being semi-structured data includes information constructed using a self-declared language and semantic delimiters.

[0016] By using unstructured and semi-structured data formats, standard complexity can be greatly simplified. It eliminates the need to define specific field parameters for various services and operations in the communication network, and also facilitates the long-term evolution of the network. Furthermore, it eliminates the need to construct communication task information according to a fixed structure, and allows for flexible description using a language with semantic elements, thereby simplifying the communication mechanism between network elements.

[0017] Secondly, a communication method is provided. This method can be executed by a second intelligent agent network element, or by a component of the second intelligent agent network element, such as a processor, chip, or chip system of the second intelligent agent network element, or by a logic module or software capable of implementing all or part of the second intelligent agent network element. The method includes:

[0018] Acquire communication task information; send communication task information to the first intelligent agent network element; the communication task information is used to declare the communication task objective to be achieved.

[0019] In one possible design, sending communication task information to the first intelligent agent network element includes: sending communication task information to the first intelligent agent network element through a second communication interface, wherein the second communication interface is an interface used to send communication task information declaring the target of the communication task.

[0020] One possible design scheme also includes discovering the first intelligent agent network element.

[0021] Optionally, discovering the first intelligent agent network element includes: sending communication task information to the network storage function; receiving response information sent by the network storage function, wherein the response information indicates the first intelligent agent network element, and the first intelligent agent network element is a network element in the communication network that can achieve the communication task objective.

[0022] In one possible design, sending communication task information to the network storage function includes: sending communication task information to the network storage function through a third communication interface, whereby the third communication interface is an interface used to send communication task information declaring the target of the communication task.

[0023] Furthermore, other technical effects of the communication method described in the second aspect can be referred to the technical effects of the communication method described in the first or third aspect, and will not be repeated here.

[0024] Thirdly, a communication method is provided, which can be executed by a network storage function, or by a component of the network storage function, such as a processor, chip, or chip system of the network storage function, or by a logic module or software capable of implementing all or part of the network storage function. The method includes:

[0025] The system receives communication task information from a second intelligent agent network element; based on the communication task information, it sends response information to the second intelligent agent network element; the communication task information is used to declare the communication task objective to be achieved, and the response information instructs a first intelligent agent network element, which is a network element in the communication network that can achieve the communication task objective corresponding to the communication task information.

[0026] Therefore, when discovering agent network elements, the network storage function can discover network elements that can achieve the communication task objective simply by declaring the communication task objective. There is no need to provide specific requirements, such as the location, capabilities, and performance of the agent network element. This supports more flexible and open discovery between agent network elements without the need for standard definitions for each agent network element, which can reduce standard complexity and improve the flexibility of the entire communication system.

[0027] In one possible design, sending response information to a second intelligent agent network element based on communication task information includes: semantically matching the communication task information with information of at least one preset intelligent agent network element to obtain a matching result; sending response information to the second intelligent agent network element based on the matching result; and the matching result indicating a first intelligent agent network element, wherein the first intelligent agent network element belongs to at least one intelligent agent network element.

[0028] Optionally, the matching result is obtained by semantically matching the communication task information with the information of at least one preset intelligent agent network element, including: semantically matching the communication task information with the information of at least one preset intelligent agent network element using an AI / ML model to obtain the matching result.

[0029] Therefore, the network storage function does not need to focus on the specific implementation of the AI / ML model. By using the AI / ML model, the communication task information can be semantically matched with the information of at least one pre-set intelligent agent network element to obtain the matching result. Compared with the existing rule-based matching, the matching complexity is reduced.

[0030] In one possible design, the information of at least one agent network element includes the role type to which at least one agent network element belongs, and the first agent network element is the agent network element of the role type that can achieve the communication task objective among the at least one agent network element.

[0031] In one possible design, the communication task information is unstructured or semi-structured data.

[0032] Optionally, communication task information is unstructured data, including information constructed in a self-declarative language;

[0033] Alternatively, communication task information may be semi-structured data, including information constructed using self-declared languages ​​and semantic delimiters.

[0034] Fourthly, a communication method is provided. This method can be executed by a network storage function, or by a component of the network storage function, such as a processor, chip, or chip system of the network storage function. It can also be implemented by a logic module or software capable of implementing all or part of the network storage function. The method includes:

[0035] Receive information from intelligent agent network elements; save information from intelligent agent network elements; intelligent agent network elements are network elements that process communication task information based on AI / ML models, and the communication task information is used to declare the communication task objectives to be achieved.

[0036] Optionally, the information of the agent element includes: the capabilities of the agent element or the rules by which the agent element is used.

[0037] Therefore, by describing the capabilities of intelligent agent network elements and / or the rules governing their use through their information, registration of these elements can be achieved. This registration method is more flexible and has greater extensibility; it can even enable personalized enhancements to intelligent agent network elements based on standard definitions. Furthermore, it eliminates the need for standard definitions for each intelligent agent network element, reducing standard complexity and improving the overall flexibility of the communication system.

[0038] In one possible design, the role type of the intelligent agent network element in the communication task is configured based on the information of the intelligent agent network element.

[0039] Optionally, the role type includes at least one of the following: orchestrating agent network elements, assembling agent network elements, executing agent network elements, connecting agent network elements, or trusted agent network elements.

[0040] Optionally, the task category to which the intelligent agent network element belongs in the communication task can be configured based on the information and role type of the intelligent agent network element.

[0041] By distinguishing only the different role types and / or task categories of intelligent agent network elements, different role types or task categories can achieve different communication task objectives or different task categories of communication task objectives. This can increase the distinction between intelligent agent network elements while ensuring flexible and personalized registration, making it easier to discover intelligent agent network elements more quickly.

[0042] In one possible design, the information of the intelligent agent network element is unstructured or semi-structured data.

[0043] Optionally, the information of the agent network element is unstructured data, including information constructed from a self-declared language; or, the information of the agent network element is semi-structured data, including information constructed from a self-declared language and semantic delimiters.

[0044] By storing agent network element information in unstructured and semi-structured data formats, standard complexity can be greatly simplified. It is not necessary to define too many specific field parameters for various agent network elements in the communication network, and it also facilitates the long-term evolution of the network. Furthermore, it is not necessary to construct communication task information according to a fixed structure. It can be flexibly described using a language with semantic elements, thereby simplifying the communication mechanism between network elements.

[0045] Fifthly, a communication device is provided. This communication device is used to perform the communication method described in any one of the first, second, third, or fourth aspects.

[0046] In this application, the communication device described in the fifth aspect can be a first intelligent agent network element or a second intelligent agent network element or a network storage function, or a chip (system) or other component or assembly, or a device containing the first intelligent agent network element or the second intelligent agent network element or the network storage function. The aforementioned chip (system) or other component or assembly can all be disposed within the first intelligent agent network element or the second intelligent agent network element or the network storage function.

[0047] It should be understood that the communication apparatus described in the fifth aspect includes modules, units, or means that implement the communication method described in any one of the first, second, third, or fourth aspects. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units for performing the functions involved in the aforementioned communication method.

[0048] Sixthly, a communication device is provided. The communication device includes a processor configured to execute the communication method described in any one of the possible implementations of the first, second, third, or fourth aspects.

[0049] In one possible design, the communication device described in the fourth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used by the communication device described in the sixth aspect to communicate with other communication devices.

[0050] In one possible design, the communication device described in the sixth aspect may further include a memory. This memory may be integrated with the processor or disposed separately. The memory may be used to store computer programs and / or data relating to the communication method described in either the first or second aspect.

[0051] In this application, the communication device described in the sixth aspect can be a first intelligent agent network element or a second intelligent agent network element or a network storage function, or a chip (system) or other component or assembly, or a device containing the first intelligent agent network element or the second intelligent agent network element or the network storage function. The aforementioned chip (system) or other component or assembly can all be disposed within the first intelligent agent network element or the second intelligent agent network element or the network storage function.

[0052] A seventh aspect provides a communication device. The communication device includes a processor coupled to a memory, the processor being configured to execute a computer program stored in the memory, such that the communication device performs the communication method described in any one of the first, second, third, or fourth aspects.

[0053] In one possible design, the communication device described in the seventh aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the fifth aspect and other communication devices.

[0054] In this application, the communication device described in the seventh aspect can be a first intelligent agent network element or a second intelligent agent network element or a network storage function, or a chip (system) or other component or assembly, or a device containing the first intelligent agent network element or the second intelligent agent network element or the network storage function. The aforementioned chip (system) or other component or assembly can all be disposed within the first intelligent agent network element or the second intelligent agent network element or the network storage function.

[0055] Eighthly, a communication device is provided, comprising: a processor and a memory; the memory is used to store a computer program, which, when executed by the processor, causes the communication device to perform the communication method described in any implementation of the first or second aspect.

[0056] In one possible design, the communication device described in the eighth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the eighth aspect and other communication devices.

[0057] In this application, the communication device described in the eighth aspect can be a first intelligent agent network element or a second intelligent agent network element or a network storage function, or a chip (system) or other component or assembly, or a device containing the first intelligent agent network element or the second intelligent agent network element or the network storage function. The aforementioned chip (system) or other component or assembly can all be disposed within the first intelligent agent network element or the second intelligent agent network element or the network storage function.

[0058] A ninth aspect provides a communication device comprising: a processor; the processor being configured to be coupled to a memory and, after reading a computer program from the memory, to execute a communication method according to the computer program as described in any one of the first, second, third, or fourth aspects.

[0059] In one possible design, the communication device described in the ninth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the ninth aspect and other communication devices.

[0060] In this application, the communication device described in the ninth aspect can be a first intelligent agent network element or a second intelligent agent network element or a network storage function, or a chip (system) or other component or assembly, or a device containing the first intelligent agent network element or the second intelligent agent network element or the network storage function. The aforementioned chip (system) or other component or assembly can all be disposed within the first intelligent agent network element or the second intelligent agent network element or the network storage function.

[0061] In a tenth aspect, a processor is provided. The processor is configured to execute the communication method described in any one of the possible implementations of the first, second, third, or fourth aspects.

[0062] Eleventhly, a communication system is provided. The communication system includes one or more first intelligent agent network elements, one or more second intelligent agent network elements, and one or more network storage functions.

[0063] In a twelfth aspect, a computer-readable storage medium is provided, comprising: a computer program or instructions; when the computer program or instructions are executed on a computer, causing the computer to perform the communication method described in any possible implementation of the first or second aspect.

[0064] In a thirteenth aspect, a computer program product is provided, comprising a computer program or instructions that, when executed on a computer, cause the computer to perform the communication method described in any possible implementation of the first or second aspect.

[0065] Furthermore, the technical effects of the communication devices described in the fifth to thirteenth aspects above can be referred to the technical effects of the communication methods described in the first, second, third, or fourth aspects above, and will not be repeated here. Attached Figure Description

[0066] Figure 1 is a schematic diagram of the architecture of a communication system;

[0067] Figure 2 is a schematic diagram of the service-oriented architecture of a 5G network;

[0068] Figure 3(a) is a schematic diagram of the architecture of the communication system provided in an embodiment of this application;

[0069] Figure 3(b) is a schematic diagram of the architecture of the communication system provided in the embodiment of this application;

[0070] Figure 4 is a flowchart illustrating the communication method provided in an embodiment of this application;

[0071] Figure 5 is a flowchart illustrating the communication method provided in an embodiment of this application;

[0072] Figure 6 is a flowchart illustrating the communication method provided in an embodiment of this application;

[0073] Figure 7 is a schematic diagram of the communication device provided in an embodiment of this application;

[0074] Figure 8 is a schematic diagram of the structure of the communication device provided in the embodiment of this application. Detailed Implementation

[0075] The technical solutions of this application can be applied to various communication systems, such as Wi-Fi systems, fourth-generation (4G) mobile communication systems (e.g., Long Term Evolution, LTE), Worldwide Interoperability for Microwave Access (WiMAX), fifth-generation (5G) mobile communication systems (e.g., New Radio, NR), and future communication systems. LTE is the long-term evolution of the Universal Mobile Telecommunications System (UMTS) technical standard developed by the 3GPP organization.

[0076] The main services included in communication systems are:

[0077] Enhanced mobile broadband (eMBB) refers to further improvements in user experience and performance based on existing mobile broadband services, representing the application scenarios most closely related to our daily lives. The most direct benefit of 5G in this regard is a significant increase in network speed; even when watching 4K high-definition video, peak speeds can reach 10Gbps. For example, eMBB refers to high-bandwidth mobile broadband services such as 3D / ultra-high-definition video.

[0078] Ultra-reliable and low-latency communication (URLLC) is characterized by high reliability, low latency, and extremely high availability. It encompasses various scenarios and applications, including industrial applications and control, traffic safety and control, remote manufacturing, remote training, and remote surgery. URLLC holds significant potential in autonomous driving. Furthermore, it is crucial for the security industry. URLLC refers to services such as autonomous driving and industrial automation that require low-latency, high-reliability connections.

[0079] Machine-type communication (MTC; also known as M2M). mMTC refers to large-scale Internet of Things (IoT) services, characterized by low cost and enhanced coverage.

[0080] Narrowband Internet of Things (NB-IoT) features wide coverage, high connectivity, low data rate, low cost, low power consumption, and superior architecture, such as massive connectivity, lower power consumption, and lower chip costs. Examples include smart water meters, smart parking systems, smart pet tracking, smart bicycles, smart smoke detectors, smart toilets, and smart vending machines.

[0081] Customer premises equipment (CPE) is essentially a mobile signal access device that receives mobile signals and forwards them as wireless Wi-Fi signals. It also converts high-speed 4G or 5G signals into wireless signals and can support a relatively large number of mobile terminals accessing the internet simultaneously. CPEs can be widely used in rural areas, towns, hospitals, offices, factories, residential communities, and other locations for wireless network access, saving the cost of laying wired networks.

[0082] Augmented reality (AR) and virtual reality (VR). Augmented reality, virtual reality, and mixed reality are all technologies that alter a user's perception of the physical world through computer-generated content.

[0083] Vehicle-to-everything (V2X) communication systems are a key technology for future intelligent transportation systems. They enable communication between vehicles, between vehicles and base stations, and between base stations. This allows for the acquisition of real-time traffic conditions, road information, pedestrian information, and other traffic data, thereby improving driving safety, reducing congestion, increasing traffic efficiency, and providing in-vehicle entertainment information.

[0084] For ease of understanding, the communication system is described below with reference to the accompanying drawings. Figure 1 is a schematic diagram of the architecture of a communication system, which includes network equipment, terminal equipment, and a core network (CN).

[0085] The network devices may include network devices 101a to 101b, and the terminal devices may include terminal devices 102a to 102b. The terminal devices can be connected to the network devices wirelessly, and the network can be connected to the core network 103 via wired or wireless means.

[0086] Among them, network devices and terminal devices can exchange information.

[0087] Terminal equipment can be a terminal with transceiver capabilities, or it can be a chip or chip system installed in the terminal equipment. This terminal equipment can also be referred to as User Equipment (UE), Access Terminal, Subscriber Unit, User Station, Mobile Station (MS), Mobile Station, Remote Station, Remote Terminal, Mobile Equipment, User Terminal, Terminal, Wireless Communication Equipment, User Agent, or User Device. The terminal devices in the embodiments of this application may be mobile phones, cellular phones, smartphones, tablets, wireless data cards, personal digital assistants (PDAs), wireless modems, handsets, laptop computers, machine-type communication (MTC) terminals, computers with wireless transceiver capabilities, virtual reality terminals, augmented reality terminals, smart home devices (e.g., refrigerators, televisions, air conditioners, electricity meters, etc.), intelligent robots, robotic arms, workshop equipment, wireless terminals in autonomous driving, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in telemedicine, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, vehicle-mounted terminals, and roadside units with terminal functions. The terminal device in this application can also be an onboard module, onboard unit, onboard component, onboard chip, or onboard unit built into a vehicle as one or more components or units. The terminal device can also be other devices with terminal functions; for example, it can be a device that performs terminal functions in D2D communication. The embodiments of this application do not limit the device form of the terminal device. The device used to implement the terminal function can be a terminal device; it can also be a device that supports the terminal in implementing the function, such as a chip system. This device can be installed in the terminal or used in conjunction with the terminal. In the embodiments of this application, the chip system can be composed of chips or include chips and other discrete devices.

[0088] Network devices can be devices with wireless transceiver capabilities, or they can be chips or chip systems located in the access network (AN) of a communication system to provide access services to terminals. For example, network devices can be called radio access network (RAN) devices, and can be RAN devices of 5G or future mobile communication systems. In future mobile communication systems, network devices may also have other naming conventions, all of which are covered within the protection scope of the embodiments of this application, and this application does not impose any limitations on them. Alternatively, network equipment can also include 5G, such as a 5G base station (next-generation node B, gNB) in a new radio (NR) system, or one or a group of antenna panels (including multiple antenna panels) of a 5G base station. It can also be network nodes constituting a gNB, transmission and reception point (TRP) or transmission point (TP), or transmission measurement function (TMF), such as a central unit (CU), distributed unit (DU), CU-control plane (CP), CU-user plane (UP), or radio unit (RU), RSU with base station functionality, or wired access gateway, or 5G core network elements, etc. Alternatively, network equipment can also include: access points (APs) in WiFi systems, wireless relay nodes, wireless backhaul nodes, various forms of macro base stations, micro base stations (also called small cells), relay stations, access points, wearable devices, vehicle-mounted equipment, etc.

[0089] CU and DU can be separate entities or included in the same network element, such as a baseband unit (BBU). RU can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). It is understood that network equipment can be CU nodes, DU nodes, or a combination of CU and DU nodes. Furthermore, CUs can be classified as network equipment in the access network (RAN) or the core network (CN), without limitation. In different systems, CUs (or CU-CPs and CU-UPs), DUs, or RUs may have different names, but their meanings will be understood by those skilled in the art. For example, in an ORAN system, a CU can also be called an O-CU (open CU), a DU can also be called an O-DU, a CU-CP can also be called an O-CU-CP, a CU-UP can also be called an O-CU-UP, and a RU can also be called an O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules. In the embodiments of this application, the form of the network device is not limited; the device used to implement the function of the network device can be the network device itself; it can also be a device capable of supporting the network device in implementing that function, such as a chip system. This device can be installed in the network device or used in conjunction with the network device.

[0090] For example, 5G communication systems employ a service-based architecture (SBA), as illustrated in Figure 2, which is a schematic diagram of an existing 5G network's service-based architecture. This service-based architecture can include a user terminal device (UE), a radio access network (R)AN, and a core network. The UE accesses the data network (DN) through the R)AN and core network equipment.

[0091] The network element (CN) may include, but is not limited to, the following network functions (NFs): user plane function (UPF), core access and mobility management function (AMF), session management function (SMF), authentication server function (AUSF), network slice selection function (NSSF), network exposure function (NEF), network exposure function repository function (NRF), policy control function (PCF), unified data management (UDM), application function (AF), or charging function (CHF), etc. It should be noted that Figure 2 only provides some examples of network elements or entities in a 5G network. This 5G network may also include network data analytics function (NWDAF) and other network elements or entities not shown in Figure 2. This application embodiment does not specifically limit these.

[0092] Network function service nodes communicate with each other through service-based interfaces (SBIs). In Figure 2, Nnef, Nnrf, Npcf, Nudm, Naf, Nausf, Namf, Nsmf, Nnssf, N1, N2, N3, N4, N6, and N9 are the sequence numbers of the service-based interfaces. As shown in Figure 2, the terminal device accesses the 5G network through the RAN device. The terminal device communicates with the AMF through the N1 interface (N1); the RAN device communicates with the AMF through the N2 interface (N2); the RAN device communicates with the UPF through the N3 interface (N3); the SMF communicates with the UP through the N4 interface (N4); and the UPF accesses the DN through the N6 interface (N6). Furthermore, the control plane functions shown in Figure 2, such as AUSF, AMF, SMF, NSSF, NEF, NRF, PCF, UDM, or AF, interact using service-based interfaces. For example, the service interface provided by AUSF is Nausf; by AMF, Namf; by SMF, Nsmf; by NSSF, Nnssf; by NEF, Nnef; by NRF, Nnrf; by PCF, Npcf; by UDM, Nudm; and by AF, Naf, etc. Related functional and interface descriptions can be found in the 5G system architecture diagram in the 23501 standard, and will not be elaborated upon here.

[0093] Each Network Provider (NF) provides a standard-defined service. Communication between NFs is explicitly defined at the level of specific service operations, that is, the service type and corresponding operation are specified in the interface message. Among them, the Service Network Provider (NRF) can register and discover various services.

[0094] Communication interfaces between Network Elements (NFs) based on the SBI definition are command-line interfaces. They use services and operations to instruct the receiver to mechanically complete specified commands, and for complex tasks, all involved operations need to be explicitly specified. In the SBI interface, the transmitted data is structured data, and the standards must have clearly defined fields. Therefore, NRF uses the NF service name provided by the NF consumer to find the NF provider that can offer the service, and can only be applied to standardized functions. In contrast, agent network elements based on large models can be considered as superfunctions, unifying all inputs and obtaining the output from the input. The functionality of agent network elements is open, guiding the completion of various complex communication tasks through prompts. Therefore, communication between network elements in existing communication networks requires relatively complex operations and is not suitable for communication between agent network elements.

[0095] To address the aforementioned technical problems, this application proposes the following technical solutions. The technical solutions in this application will now be described in conjunction with the accompanying drawings.

[0096] This application will present various aspects, embodiments, or features relating to systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible.

[0097] Furthermore, in the embodiments of this application, words such as "exemplarily" and "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as an "example" in this application should not be construed as being better or more advantageous than other embodiments or designs. Rather, the use of the word "example" is intended to present the concept in a specific manner.

[0098] First, in this application, "for indicating" can include both direct and indirect indication. When describing "information" for indicating A, it can include whether the information directly indicates A or indirectly indicates A, but does not necessarily mean that the information carries A.

[0099] The information indicated by a given piece of information is called the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as, but not limited to, directly indicating the information to be indicated, such as the information to be indicated itself or its index. It can also be indirectly indicated by indicating other information, where there is a relationship between the other information and the information to be indicated. It can also indicate only a part of the information to be indicated, while the other parts are known or pre-agreed upon. For example, the indication of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing the indication overhead to some extent. At the same time, common parts of various pieces of information can be identified and indicated uniformly to reduce the indication overhead caused by individually indicating the same information.

[0100] Furthermore, the specific indication method can also be any existing indication method, such as, but not limited to, the above-mentioned indication methods and their various combinations. Specific details of various indication methods can be found in existing technologies, and will not be repeated here. As described above, for example, when multiple pieces of information of the same type need to be indicated, the indication methods for different pieces of information may differ. In the specific implementation process, the required indication method can be selected according to specific needs. This application embodiment does not limit the selected indication method; therefore, the indication methods involved in this application embodiment should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated.

[0101] The information to be instructed can be sent as a whole or divided into multiple sub-information messages, and the sending period and / or timing of these sub-information messages can be the same or different. This application does not limit the specific sending method. The sending period and / or timing of these sub-information messages can be predefined, for example, according to a protocol, or configured by the transmitting device by sending configuration information to the receiving device. This configuration information can include, for example, but not limited to, one or a combination of at least two of radio resource control (RRC) signaling, medium access control (MAC) layer signaling, and physical layer signaling. MAC layer signaling includes, for example, a MAC control element (CE); physical (PHY) layer signaling includes, for example, downlink control information (DCI).

[0102] Second, in the embodiments shown below, the first, second, and various numerical designations are merely distinctions for descriptive convenience and are not intended to limit the scope of the embodiments of this application. For example, to distinguish different indication information.

[0103] Third, "pre-defined," "pre-configured," or "pre-specified" can be achieved by pre-saving corresponding codes, tables, or other means of indicating relevant information in the device (e.g., including terminal devices and network devices), or by pre-defining them in a protocol. This application does not limit the specific implementation method. "Saving" can refer to saving in one or more memories. These memories can be separate installations or integrated into the encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the decoder, processor, or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0104] Fourth, the “protocol” involved in the embodiments of this application may refer to standard protocols in the field of communication, such as 3GPP’s LTE protocols (such as technical specification (TS) 36, i.e., the TS36 series of technical specifications), NR protocols (such as the TS38 series of technical specifications), and related protocols applied to future communication systems. This application does not limit this.

[0105] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0106] The network architecture and business scenarios described in the embodiments of this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0107] To facilitate understanding of the embodiments of this application, the communication system applicable to the embodiments of this application will be described in detail first using the communication system shown in FIG3(a) as an example. Exemplarily, FIG3(a) is a schematic diagram of the architecture of a communication system to which the method provided in the embodiments of this application is applicable.

[0108] For example, the communication system includes a first agent network element and a second agent network element. The first agent network element and the second agent network element can be agent network elements in the communication network shown in Figure 3(b) below; for example, the first agent network element and the second agent network element can be any role type of agent network element in the communication network, such as orchestration agent network element, assembly agent network element, trusted agent network element, connection agent network element, or execution agent network element; or they can be agent network elements of any task category under a certain role type; and so on.

[0109] Optionally, the communication system also includes a network storage function. The network storage function can be a function deployed on an agent network element (such as a first agent network element, a second agent network element, or other agent network elements), and can also be called an Agent Repository Function (ARF). "ARF" is merely an exemplary description; it can also be replaced with agent warehousing function, agent storage network element, etc. Alternatively, the network storage function can also be a node or device deployed in the communication network, such as also an agent network element; this embodiment does not impose limitations.

[0110] In this communication system, the first intelligent agent network element acquires communication task information, which is used to declare the communication task objective to be achieved; it executes the operation corresponding to the communication task objective and obtains the execution result; the operation corresponding to the communication task objective is determined based on the communication task information. The intelligent agent network element can process the declared objective information to obtain the operations required to achieve the objective. Therefore, when communicating between intelligent agent network elements, the intelligent agent network element only needs to declare the communication task objective to be achieved in the communication task information, without needing to concern itself with how the other network element specifically implements it. Signaling interaction can omit instructions for specific services and operations, thereby improving the interoperability efficiency of network elements in the communication network, i.e., improving communication efficiency.

[0111] For example, Figure 3(b) is a schematic diagram of the architecture of a communication system to which the method provided in the embodiments of this application applies. The communication system includes: a terminal device, a network device, an application network data anchor / proxy (A-GW), an application network instance, and a communication network based on intelligent agent network elements. The communication network is not limited; for example, it can be the core network in 5G; for example, it can also be a wireless network system, a 4G mobile communication system, a network in a new radio interface system, etc. Intelligent agent network elements can be devices or nodes in a communication network that have deployed AI or machine learning (ML) models. Machine learning models can be logistic regression, support vector machines, decision trees, random forests, extreme gradient boosting (XGBoost), etc.; AI models can be multilayer perceptrons, fully connected neural networks, long short-term memory neural networks, bidirectional encoder representations from transformers (BERT) models based on transformers, large language models (LLM), etc. For example, large language models can be deployed, such as generative pre-trained transformer (GPT) models based on transformer architectures; large models deployed in communication networks to perform communication services can also be called network large models (NetGPT).

[0112] For example, if the intelligent agent network elements in the core network are deployed with large models, the core network based on these intelligent agent network elements can, upon receiving a user's intent request, leverage the intent understanding and generation capabilities of the large models to orchestrate the required network and application functions on demand for the user, and configure network devices and user terminals to obtain a customized application network instance. This application network instance can efficiently serve the user and other users with similar needs.

[0113] For example, a communication network based on agent network elements can include agent network elements with different roles, such as planning agents, assembling agents, trusted agents, connection agents, and execution agents.

[0114] The orchestration agent network element is responsible for orchestrating communication tasks. It decomposes user intentions into a series of sub-communication tasks, orchestrates the communication task topology, and performs final resource reclamation after the communication tasks are completed, offering flexibility and efficiency.

[0115] The assembly of intelligent agent network elements, based on the results of communication task orchestration (communication task topology), calls the tools library to match corresponding functions (including network functions and application functions) for each sub-communication task, resulting in the application network topology. This means that the interconnection relationships between functions are uniformly established and interfaces are connected by the assembled intelligent agent network elements.

[0116] The executing agent network element is responsible for the management and control of application network instances. It schedules resources for the assembled application network topology for deployment and operation; and monitors network status, making timely optimizations and adjustments. For example, after receiving a communication task topology, the executing agent network element needs to distinguish which functions need to be deployed in the core network and which need to be implemented through configuring network devices and user terminals. For the former, the executing agent network element can select hardware resources for these functions using a large model, including the number of central processing units (CPUs) and graphics processing units (GPUs) required, memory size, and the quality of service (QoS) requirements of the sub-communication tasks, such as execution time and energy consumption; then, it creates an execution environment for the function on the corresponding hardware resources and loads the execution program. For the latter, the executing agent network element initiates the corresponding function to the connecting agent network element for task configuration. The application network instance is the application network topology deployed and run by the executing agent network element. The application network data proxy is used to proxy communication between the application network instance and network devices and connecting agent network elements.

[0117] Trusted intelligent agent network elements can achieve security and privacy protection, encryption algorithms, and blockchain integration.

[0118] The connection between the terminal device and the application network instance is established based on the connection agent network element. The connection agent network element calls RAN resources to establish data routing between the terminal device and the application network instance.

[0119] For example, each type of agent network element can deploy one or more agent network element instances. These agent network elements can be used to handle communication tasks of different task categories. Specifically, orchestration agent network elements, assembly agent network elements, trusted agent network elements, connection agent network elements, and execution agent network elements can each include one or more agent network elements that handle communication tasks of different task categories. For example, task categories can include communication tasks such as vehicle-to-everything (V2X), augmented reality or virtual reality, the Internet of Things (IoT), industrial automation, and multimedia playback. It is understood that the above examples do not limit the task categories; in practical applications, they can be divided at a smaller or larger granularity. For example, at a smaller granularity, V2X communication tasks can also be divided into navigation, intelligent driving, and autonomous driving communication tasks. It is understood that agent network elements of different task categories can include one or more agent network elements. The terms orchestration agent network elements, assembly agent network elements, trusted agent network elements, connection agent network elements, and execution agent network elements are merely exemplary representations; other representations can also be used.

[0120] It should be understood that the communication method provided in this application embodiment can be applied to the communication system shown in Figure 3(a), such as communication between orchestration agent network elements and assembly agent network elements, between assembly agent network elements and trusted agent network elements, between assembly agent network elements and execution agent network elements, etc. Specific implementations can be found in the following method embodiments, which will not be repeated here. The solutions in this application embodiment can also be applied to other communication systems, and the corresponding names can be replaced by the names of the corresponding functions in other communication systems.

[0121] It should also be understood that Figures 3(a) and 3(b) are simplified schematic diagrams for ease of understanding only, and the communication system may also include other network devices, and / or other terminal devices, and / or intelligent agent network elements, which are not shown in Figures 3(a) and 3(b).

[0122] The interaction process between devices in the above-described communication system will be specifically described below with reference to Figure 4, through a method embodiment. The communication method provided in this application embodiment can be applied to the above-described communication system, such as the interaction between the first intelligent agent network element and the second intelligent agent network element, which will be described in detail below.

[0123] As shown in Figure 4, the flow of this communication method is as follows:

[0124] S401, the first intelligent agent network element acquires communication task information.

[0125] Communication task information is used to declare the communication task objectives to be achieved.

[0126] The communication task objectives declared in the communication task information for different intelligent agent network elements may be the same or different. For example, if the first intelligent agent network element is an assembly intelligent agent network element, the corresponding communication task objective may include matching corresponding functions for each sub-communication task to obtain the application network topology; if the first intelligent agent network element is an execution intelligent agent network element, the corresponding communication task objective may include deploying and running the application network topology; if the first intelligent agent network element is a connection intelligent agent network element, the corresponding communication task objective may include establishing data routing between the terminal device and the application network instance; and so on.

[0127] Taking autonomous driving as an example, assuming the second intelligent agent network element is an intelligent agent network element with autonomous driving as its task category within the orchestration intelligent agent network element, and the first intelligent agent network element can be an intelligent agent network element with autonomous driving as its task category within the assembly intelligent agent network element, the communication task objective includes matching corresponding functions for each sub-communication task of autonomous driving. Alternatively, assuming the second intelligent agent network element is an intelligent agent network element with autonomous driving as its task category within the assembly intelligent agent network element, and the first intelligent agent network element can be an intelligent agent network element with autonomous driving as its task category within the execution intelligent agent network element, the communication task objective includes deploying and running the application network topology for autonomous driving.

[0128] The specific implementation method for the first intelligent agent network element to obtain communication task information is not limited. For example, it can generate communication task information corresponding to the next communication task based on the execution result of the previous communication task, or it can receive communication task information from other devices or nodes.

[0129] In one possible implementation, the first intelligent agent network element can receive communication task information from the second intelligent agent network element. Specifically, the second intelligent agent network element acquires the communication task information and sends it to the first intelligent agent network element; correspondingly, the first intelligent agent network element receives the communication task information from the second intelligent agent network element. The specific implementation method for the second intelligent agent network element to acquire the communication task information is not limited; for example, it can generate the corresponding communication task information from its own execution results, or it can receive the communication task information from other devices or nodes.

[0130] For example, suppose the user terminal is car 1, and the user's intention is to activate intelligent driving at location 1. The user terminal sends user information to a second intelligent agent network element. The second intelligent agent network element is an intelligent agent network element in the orchestration network element whose task category is intelligent driving. After receiving the user information, this intelligent agent network element can decompose the user's intention into a series of sub-communication tasks based on an AI / ML model. These sub-communication tasks might include: obtaining environmental information of car 1 at location 1, path planning, vehicle control, vehicle-to-infrastructure (V2I) communication, localization and navigation, and high-precision map processing. The execution result is the communication task topology. The second intelligent agent network element then generates communication task information based on this topology. This communication task information declares the communication task objectives to be achieved, including matching corresponding functions to each sub-communication task (the sub-communication task of intelligent driving). It is understandable that the sub-communication task can also declare its own sub-communication task objectives.

[0131] In conjunction with the above embodiments, for communication between intelligent agent network elements, a communication interface can be defined, such as an agent-based interface (ABI). This communication interface is a declarative interface, capable of receiving and / or sending information declaring the communication task objectives to be achieved, without needing to provide specific services and operation instructions. That is, the second intelligent agent network element can send communication task information to the first intelligent agent network element through the second communication interface, which is the interface used to send communication task information declaring the communication task objectives; correspondingly, the first intelligent agent network element can receive communication task information from the second intelligent agent network element through the first communication interface, which is the interface used to receive communication task information declaring the communication task objectives.

[0132] For example, assuming the first intelligent agent network element is an assembly intelligent agent network element, the first communication interface is used to receive communication task information declaring that the communication task objective includes matching corresponding functions for each sub-communication task, and the second communication interface is used to send communication task information declaring that the communication task objective includes matching corresponding functions for each sub-communication task; assuming the first intelligent agent network element is an execution intelligent agent network element, the first communication interface is used to receive communication task information declaring that the communication task objective includes deploying and running the application network topology, and the second communication interface is used to receive communication task information declaring that the communication task objective includes deploying and running the application network topology.

[0133] Taking intelligent driving as an example, assuming that the first intelligent agent network element is an assembled intelligent agent network element with intelligent driving as the task category, the first communication interface is an interface used to receive communication task information that declares the communication task objectives, including obtaining environmental information of the location 1 of the car 1, path planning, driving control, vehicle-road cooperation, positioning and navigation, high-precision map processing and other functions that match the corresponding functions.

[0134] Therefore, by defining a declarative communication interface for intelligent agents, efficient communication between intelligent agent network elements can be achieved. The term "intelligent agent interface" is merely an exemplary description and can be replaced with intelligent agent interface, intelligent agent communication interface, intelligent interface, etc.

[0135] It is understandable that the first communication interface can also be an interface used to send communication task information declaring the communication task target in the first intelligent agent network element; or the first intelligent agent network element can be configured to send an interface declaring the communication task target. The second communication interface can be an interface used to receive communication task information declaring the communication task target in the second intelligent agent network element; or the second intelligent agent network element can be configured to receive communication task information declaring the communication task target.

[0136] S402. The first intelligent agent network element performs the operation corresponding to the communication task objective and obtains the execution result.

[0137] The operation corresponding to the communication task objective is determined based on the communication task information.

[0138] In one possible design, communication task information is processed based on an AI / ML model to obtain the operations corresponding to the communication task objectives. For example, the assembled intelligent agent network element can use an AI / ML model to parse the semantic elements in the received communication task information to obtain the corresponding operations for each sub-communication task. Alternatively, the executing intelligent agent network element can parse the semantic elements in the received communication task information to obtain the operations corresponding to deploying and running the application network topology.

[0139] In one possible design, the first intelligent agent network element, based on an AI / ML model, executes the operation corresponding to the communication task objective and obtains the execution result.

[0140] For example, the assembled intelligent agent network element is based on an AI / ML model and calls the tools library to match the corresponding function for each sub-communication task. For example, based on the AI / ML model, the functions in the tools library are semantically matched with the sub-communication task objectives declared in the sub-communication task, so as to match the corresponding function for each sub-communication task.

[0141] The execution of intelligent agent network elements can be based on AI / ML models to schedule resources for the assembled application network topology for deployment and operation, as described in Figure 3(b), which will not be repeated here.

[0142] Because AI / ML models have powerful data processing and analysis capabilities, they can flexibly process communication task information, obtain relatively reliable operations corresponding to communication task objectives, and accurately execute the corresponding operations. Furthermore, they can better support communication between intelligent agent network elements by simply declaring the communication task objective to be achieved. The following are some more specific examples to illustrate this.

[0143] For example, if the second intelligent agent network element is an intelligent agent network element in the orchestration intelligent agent network element whose task category is intelligent driving, then the first intelligent agent network element can be an intelligent agent network element in the assembly intelligent agent network element whose task category is intelligent driving. After receiving the communication task information, the assembly intelligent agent network element can use an AI / ML model to parse the semantics in the communication task information to obtain the communication task objective as matching the corresponding function for each sub-communication task. Furthermore, the assembly intelligent agent network element can then use the AI / ML model to match the corresponding function for each sub-communication task, i.e., matching the corresponding functions for obtaining environmental information of the location 1 of vehicle 1, path planning, driving control, vehicle-to-infrastructure (V2I) communication, localization and navigation, and high-precision map processing, respectively.

[0144] Furthermore, there are no restrictions on the specific form of the execution results. For example, the execution results of orchestrating intelligent agent network elements may include communication task topology; the execution results of assembling intelligent agent network elements may include application network topology; the execution results of executing intelligent agent network elements may include hardware resources selected for functions, quality of service of sub-communication tasks, deployed application network instances, etc.; the execution results of trusted intelligent agent network elements may include various encrypted data, blockchain, etc.; and the execution results of connecting intelligent agent network elements may include data routing between the UE and application network instances.

[0145] In summary, intelligent agent network elements can process the information of declared goals to obtain the operations required to achieve the goals. Therefore, when intelligent agent network elements communicate with each other, the intelligent agent network elements only need to declare the communication task goals to be achieved in the communication task information, without needing to care about how the other network element implements them. The signaling interaction can omit the instructions of specific services and operations, thereby improving the docking efficiency of each network element in the communication network, that is, improving communication efficiency.

[0146] In conjunction with the above embodiments, for different execution results, the first intelligent agent network element may send information indicating the execution result to the second intelligent agent network element, or it may not send such information. The first intelligent agent network element may send information indicating the execution result to the second intelligent agent network element. Correspondingly, the second intelligent agent network element receives the information indicating the execution result from the first intelligent agent network element, where the execution result is the result obtained by the first intelligent agent network element performing the operation corresponding to the communication task objective. For example, the assembly intelligent agent network element may send information indicating the execution result to the orchestration intelligent agent network element, such as sending information indicating that a corresponding function has been matched for the sub-communication task, or it may send information about the function matched for each sub-communication task. The execution intelligent agent network element may not send the execution result to the assembly intelligent agent network element.

[0147] In conjunction with the above embodiments, the communication task information can be unstructured data or semi-structured data.

[0148] For example, communication task information as unstructured data includes information constructed in a self-declaring language. A self-declaring language may contain semantic elements itself; for example, it may be a natural language or a computer language that contains semantic elements.

[0149] For example, the communication task information is semi-structured data, including information constructed from a self-declared language and semantic delimiters. Semantic delimiters can be used to separate semantic elements.

[0150] For example, suppose that the orchestration agent network element in the communication network orchestrates communication tasks, and the assembly agent network element matches the corresponding functions to the communication tasks.

[0151] If the communication task information is unstructured data, the communication task information sent by the orchestrating agent network element to the assembling agent network element can be described as follows: obtaining environmental information of the location 1 of the car 1, path planning, driving control, vehicle-road cooperation, positioning and navigation, high-precision map processing, etc., and matching the corresponding functions respectively.

[0152] For example, in English, the declared communication task objective could be described as: You need to find appropriate tools to get the 3 closest BSs at Jinqiao road 2222. Send back the BS list sorted from near to far.

[0153] The communication task information here is entirely constructed in a self-declaring language (natural language), containing semantic elements. Understandably, in practical applications, it can be converted into a language that computers can process. Assembling intelligent agent network elements allows them to independently understand the semantic elements in this natural language description and match appropriate tools.

[0154] If the communication task information is semi-structured data, the communication task objective declared in the communication task information sent by the orchestration agent network element to the assembly agent network element can be described as:

[0155] Sub-communication tasks: acquiring environmental information of the location 1 of vehicle 1, path planning, driving control, vehicle-road cooperation, positioning and navigation, high-precision map processing, etc.

[0156] Objective: To match the corresponding functions for each sub-communication task.

[0157] For example, the declared communication task objective can be described as:

[0158] target:find appropriate tools to get the 3 closest BSs at given location;

[0159] Input: Jinqiao road 2222;

[0160] Output:BS list sorted from near to far.

[0161] The self-declared language includes: find appropriate tools to get the 3 closest BSs at a given location, Jinqiao road 2222, BS list sorted from near to far, etc.; the separators include:; etc. That is, the interface between intelligent agent network elements can use natural language as input, enabling interaction between intelligent agent network elements through natural language.

[0162] It is understandable that other information communicated between the first agent network element and the second agent network element can also be structured or semi-structured data, such as the response information and agent network element information described below.

[0163] In summary, unstructured and semi-structured data formats can significantly simplify standard complexity, eliminating the need to define specific field parameters for various services and operations in the communication network, and facilitating the long-term evolution of the network. Furthermore, communication task information does not need to be constructed according to a fixed structure; it can be flexibly described using a language with semantic elements, thereby simplifying the communication mechanism between network elements.

[0164] In a communication network, there may be many intelligent agent network elements. The second intelligent agent network element needs to discover the first intelligent agent network element that can achieve the communication task objective corresponding to the communication task information. The following will describe the method in detail with reference to Figure 5. The communication method provided in this application embodiment can be applied to the above-mentioned communication system, such as the interaction between the second intelligent agent network element and the network storage function.

[0165] As shown in Figure 5, the flow of this communication method is as follows:

[0166] S501, the second intelligent agent network element sends communication task information to the network storage function; correspondingly, the network storage function receives the communication task information from the second intelligent agent network element.

[0167] In one possible design, the second intelligent agent network element sends communication task information to the network storage function through a third communication interface. The network storage function receives the communication task information from the second intelligent agent network element through a fourth communication interface. The third communication interface is used to send communication task information declaring the communication task objective; the fourth communication interface is used to receive communication task information declaring the communication task objective. Specific descriptions of the third and fourth communication interfaces can be found in the first and second communication interfaces, and will not be repeated here.

[0168] It is understood that the third communication interface may be the same as or a different interface from the second communication interface mentioned above; the fourth communication interface may also be an interface used to send communication task information that declares the communication task target in the storage network function; or it may be configured for the network storage function to send communication task information that declares the communication task target.

[0169] S502, the network storage function sends response information to the second intelligent agent network element according to the communication task information; correspondingly, the second intelligent agent network element receives the response information sent by the network storage function.

[0170] In one possible design, the network storage function performs semantic matching between communication task information and information of at least one preset intelligent agent network element to obtain a matching result; based on the matching result, it sends response information to the second intelligent agent network element; the matching result indicates the first intelligent agent network element, and the first intelligent agent network element belongs to at least one intelligent agent network element.

[0171] The information of at least one preset intelligent agent network element can be referred to the information of the intelligent agent network element in the embodiment of Figure 6 below, which will not be repeated here; or, the information of at least one preset intelligent agent network element can also be stored in each intelligent agent network element.

[0172] The matching result is not restricted; for example, it can be a probability distribution result, such as the similarity of 98% for the assembled agent network element, 1.5% for the executing agent network element, 0.3% for the connecting agent network element, and 0.2% for the trusted agent network element, in which case the matching result indicates the assembled agent network element; or, the matching result can also directly point to the first agent network element, such as directly outputting the matching result as the assembled agent network element.

[0173] For example, the network storage function itself is equipped with an AI / ML model and has semantic matching capabilities, which can semantically match communication task information with the information of each intelligent agent network element.

[0174] For example, the network storage function can invoke NetGPT deployed in the communication network to perform semantic matching between the communication task information and the information of at least one preset intelligent agent network element to obtain the matching result.

[0175] For example, the communication task objective includes matching the corresponding function for each sub-communication task. When semantically matching the information of the agent network element (Role definition - Select proper network entities and / or application function(s) for each task and determine the function topology based on task dependency relationship), the highest similarity is found, and the matching result points to the assemble agent network element.

[0176] For example, if the communication task objective includes deploying and running the application network topology, and the semantic similarity is highest when performing semantic matching with the information of the intelligent agent network element (Roledefinition—Deploy function instances on computing resources, chain the function instances, monitor the operational status of these functions, and optimize), then the matching result points to the execution intelligent agent network element.

[0177] Furthermore, the response information indicates the first intelligent agent network element. The first intelligent agent network element is one capable of achieving the communication task objective corresponding to the communication task information. For example, the communication task objective might include matching corresponding functions for each sub-communication task to obtain the application network topology, with the response information indicating the assembly of intelligent agent network elements; or it might include deploying and running the application network topology, with the response information indicating the execution of intelligent agent network elements; and so on. Therefore, when discovering intelligent agent network elements, the network storage function can discover network elements capable of achieving the desired communication task objective simply by declaring it. This supports the discovery of more flexible and open intelligent agent network elements without requiring standard definitions for each element, reducing standard complexity and improving the overall flexibility of the communication system.

[0178] Therefore, the network storage function does not need to focus on the specific implementation of the AI / ML model. By using the AI / ML model, the communication task information can be semantically matched with the information of at least one pre-set intelligent agent network element to obtain the matching result. Compared with the existing rule-based matching, the matching complexity is reduced.

[0179] Optionally, the information of at least one agent network element includes the role type to which at least one agent network element belongs, and the first agent network element is the agent network element of the role type that can achieve the communication task objective among the at least one agent network element.

[0180] For example, the network storage function is configured with role types for each intelligent agent network element. The network storage function can perform semantic parsing on communication task information, extract key features, determine the role type based on the key features, and then perform semantic matching between the communication task information and the information of the intelligent agent network element under that role type. For example, by performing semantic parsing on the communication task objective and extracting keywords such as matching and function, it can be mapped to the assembly intelligent agent network element, and then the communication task information can be semantically matched with the information of the assembly intelligent agent network element.

[0181] For example, after determining the role type based on key features, the network storage function then determines the task category under that role type, and then performs semantic matching between the communication task information and the information of the intelligent agent network element under that task category. For instance, by performing semantic parsing on the communication task objective and extracting keywords such as matching, function, navigation, vehicle, location, and intelligent driving, the assembly intelligent agent network element can be located, and then the intelligent agent network element with the task category of intelligent driving can be located. The communication task information is then semantically matched with the information of the assembly intelligent agent network element with the task category of intelligent driving.

[0182] For example, the network storage function determines the task category based on key features, and then performs semantic matching between the communication task information and the information of the intelligent agent network element under that task category. For instance, by performing semantic parsing on the communication task objective and extracting keywords such as navigation, vehicle, location, and intelligent driving, the intelligent agent network element with the task category of intelligent driving can be located, and then the communication task information can be semantically matched with the information of the intelligent agent network element with the task category of intelligent driving.

[0183] By distinguishing between different role types or task categories of intelligent agent network elements, different role types or task categories can achieve different communication task objectives or different task categories of communication task objectives. This can increase the distinction between intelligent agent network elements while ensuring flexible and personalized registration, making it easier to discover intelligent agent network elements more quickly.

[0184] A communication network may contain many types of intelligent agent network elements, and each type of intelligent agent network element can be deployed in multiple instances according to the task category during implementation, thereby avoiding a single intelligent agent network element becoming a bottleneck. Therefore, it is necessary to register intelligent agent network elements of different categories so that when intelligent agent network elements are discovered, the intelligent agent network element that can achieve the corresponding communication task objective can be accurately located. The following will describe the method embodiment in detail with reference to Figure 6. The communication method provided in this application embodiment can be applied to the above-mentioned communication system, such as the interaction between the second intelligent agent network element and the network storage function.

[0185] As shown in Figure 6, the flow of this communication method is as follows:

[0186] S601, the intelligent agent network element sends its information to the network storage function; correspondingly, the network storage function receives the information from the intelligent agent network element.

[0187] An intelligent agent network element is a network element in a communication network that processes communication task information based on an AI / ML model. The communication task information is used to declare the communication task objective to be achieved. It can be any intelligent agent network element in the aforementioned communication system, or it can be the aforementioned first intelligent agent network element or second intelligent agent network element.

[0188] Information about an intelligent agent network element includes: the capabilities of the intelligent agent network element and / or the rules governing its use. The capabilities of an intelligent agent network element can represent the communication task objectives it can achieve; the rules governing its use can represent how to use the intelligent agent network element, what constraints and limitations exist, and what effects it brings. For example, the ability to orchestrate an intelligent agent network element can include decomposing user intent into a series of sub-communication tasks and orchestrating a communication task topology. The ability to execute an intelligent agent network element can include: scheduling resources for deployment and operation of the assembled application network topology; and monitoring network status and making timely optimizations and adjustments.

[0189] In one possible design, the information of the intelligent agent network element is unstructured or semi-structured data.

[0190] For example, the information of the agent network element is unstructured data, including information constructed from natural language.

[0191] For example, the information of the agent network element is semi-structured data, which includes both structured data and information constructed from natural language. The following example uses English as the information of the agent network element:

[0192] For example, the information for orchestrating intelligent agent network elements can be: Understand the customer's requirement for a customized slice, orchestrate, and decompose the requirement into multiple executable tasks.

[0193] The information for assembling intelligent agent network elements can be: Select proper network entities and / or application function(s) for each task and determine the function topology based on task dependency relationship.

[0194] S602, Network storage function saves information of intelligent agent network elements.

[0195] In other words, the intelligent agent network element has completed its registration at the network storage function. Registration of the intelligent agent network element is achieved by describing its capabilities and / or the rules governing its use using a self-declarative language. This registration method is more flexible, has richer extensibility, and can even enable personalized enhancements to the intelligent agent network element based on standard definitions.

[0196] In conjunction with the foregoing embodiments, the network storage function can also configure the role type of the intelligent agent network element in the communication task based on the information of the intelligent agent network element. The role type includes at least one of the following: orchestrating intelligent agent network elements, assembling intelligent agent network elements, executing intelligent agent network elements, connecting intelligent agent network elements, or trusted intelligent agent network elements. As shown in Table 1 below, assuming the intelligent agent network element information is in English, this is an example.

[0197] Table 1

[0198] For example, the task category to which the intelligent agent network element belongs in the communication task can also be configured according to the information and role type of the intelligent agent network element.

[0199] For example, as shown in Table 2 below: role types can include Planning Agent, Assemble Agent, etc., and task categories can include V2X, IoT, etc.

[0200] Table 2

[0201] The specific role types and task categories can be found in the relevant descriptions of the communication system shown in Figure 3(b), and will not be repeated here. It is understood that the information in Tables 1 and 2 can be translated into a language that a computer can process during implementation.

[0202] In summary, by distinguishing between different role types and / or task categories of intelligent agent network elements, different role types or task categories can achieve different communication task objectives or different task categories of communication task objectives. This can increase the distinction between intelligent agent network elements while ensuring flexible and personalized registration, making it easier to discover intelligent agent network elements more quickly.

[0203] The communication method provided by the embodiments of this application has been described in detail above with reference to Figures 4-6. The communication apparatus used to perform the communication method provided by the embodiments of this application is described in detail below with reference to Figures 7 and 8.

[0204] For example, FIG7 is a schematic diagram of the structure of a communication device provided in an embodiment of this application. As shown in FIG7, the communication device 700 includes a transceiver module 701 and a processing module 702. For ease of explanation, FIG7 only shows the main components of the communication device.

[0205] In some embodiments, the communication device 700 may be adapted to the communication system shown in FIG3(a) to perform the function of the first intelligent agent network element in the communication method shown in FIG4.

[0206] The transceiver module 701 is used to acquire communication task information, which is used to declare the communication task objectives to be achieved.

[0207] The processing module 702 is used to execute the operation corresponding to the communication task target and obtain the execution result; the operation corresponding to the communication task target is determined according to the communication task information.

[0208] In one possible design, the transceiver module 701, when acquiring communication task information, can be used to receive communication task information from the second intelligent agent network element through a first communication interface. The first communication interface is an interface for receiving communication task information that declares the communication task target.

[0209] In one possible design, the processing module 702, when performing the operation corresponding to the communication task target, can be used to perform the operation corresponding to the communication task target based on an artificial intelligence (AI) / machine learning (ML) model.

[0210] Optionally, the processing module 702 is used to perform operations corresponding to the communication task target based on the AI / ML model. It can be used to process communication task information based on the AI / ML model to obtain the operations corresponding to the communication task target and execute the operations corresponding to the communication task target.

[0211] In one possible design, the communication task information is unstructured or semi-structured data.

[0212] Optionally, communication task information being unstructured data includes information constructed using a self-declared language; or, communication task information being semi-structured data includes information constructed using a self-declared language and semantic delimiters.

[0213] Optionally, the transceiver module 701 may include a receiving module and a transmitting module (not shown in FIG7). The transceiver module is used to implement the transmitting and receiving functions of the communication device 700.

[0214] Optionally, the communication device 700 may further include a storage module that stores programs or instructions. When the transceiver module 701 executes the program or instructions, the communication device 700 can perform the functions of the first intelligent agent network element in the communication method shown in FIG4.

[0215] It should be understood that the transceiver module 701 can be implemented by a transceiver or transceiver-related circuit components, and can be a transceiver or transceiver unit.

[0216] Furthermore, the communication device 700 can be a first intelligent agent network element, a chip (system), or other components or parts, or a device containing a first intelligent agent network element; this application does not limit this. The aforementioned chip (system), or other components or parts, can all be disposed within the first intelligent agent network element or the second intelligent agent network element. The technical effects of the communication device 700 can be referred to the technical effects of the communication method shown in Figure 4, and will not be repeated here.

[0217] In other embodiments, the communication device 700 may be adapted to the communication system shown in FIG3(a) to perform the function of the second intelligent agent network element in the communication method shown in FIG4.

[0218] The processing module 702 is used to obtain communication task information, which is used to declare the communication task objectives to be achieved.

[0219] The transceiver module 701 is used to send communication task information to the first intelligent agent network element.

[0220] In one possible design, the transceiver module 701, when used to send communication task information to the first intelligent agent network element, can also be used to send communication task information to the first intelligent agent network element through a second communication interface, which is an interface used to send communication task information declaring the target of the communication task.

[0221] In one possible design, the processing module 702 is also used to discover the first intelligent agent network element.

[0222] Optionally, the processing module 702, when discovering the first intelligent agent network element, can be used to send communication task information to the network storage function; receive response information sent by the network storage function, the response information indicating the first intelligent agent network element, the first intelligent agent network element being a network element in the communication network capable of achieving the communication task objective.

[0223] In one possible design, the transceiver module 701 is used to send communication task information to the network storage function. It can be used to send communication task information to the network storage function through a third communication interface, which is an interface for sending communication task information that declares the target of the communication task.

[0224] Optionally, the communication device 700 may further include a storage module that stores programs or instructions. When the transceiver module 701 executes the program or instructions, the communication device 700 can perform the functions of the second intelligent agent network element in the communication method shown in FIG4.

[0225] It should be understood that the transceiver module 701 can be implemented by a transceiver or transceiver-related circuit components, and can be a transceiver or transceiver unit.

[0226] Furthermore, the communication device 700 can be a second intelligent agent network element, a chip (system) or other component or assembly disposed in the aforementioned second intelligent agent network element, or a device containing the second intelligent agent network element; this application embodiment does not limit this. The technical effects of the communication device 700 can be referred to the technical effects of the communication method shown in FIG4, and will not be repeated here.

[0227] In other embodiments, the communication device 700 may be adapted to the communication system shown in FIG3(a) to perform the functions of the network storage function in the communication method shown in FIG5 or FIG6.

[0228] Example 1: Transceiver module 701 is used to receive communication task information from the second intelligent agent network element. The communication task information is used to declare the communication task objective to be achieved.

[0229] The processing module 702 is used to control the transceiver module 701 to send response information to the second intelligent agent network element according to the communication task information. The response information indicates the first intelligent agent network element, which is a network element in the communication network that can realize the communication task target corresponding to the communication task information.

[0230] In one possible design, the processing module 702 can be used to obtain a matching result by semantically matching the communication task information with the information of at least one preset intelligent agent network element; according to the matching result, control the transceiver module 701 to send response information to the second intelligent agent network element; the matching result indicates the first intelligent agent network element, and the first intelligent agent network element belongs to at least one intelligent agent network element.

[0231] The processing module 702 can be used to semantically match the communication task information with the information of at least one preset intelligent agent network element through an AI / ML model to obtain the matching result.

[0232] In one possible design, the information of at least one agent network element includes the role type to which at least one agent network element belongs, and the first agent network element is the agent network element of the role type that can achieve the communication task objective among the at least one agent network element.

[0233] In one possible design, the communication task information is unstructured or semi-structured data.

[0234] Optionally, communication task information is unstructured data, including information constructed in a self-declarative language;

[0235] Alternatively, communication task information may be semi-structured data, including information constructed using self-declared languages ​​and semantic delimiters.

[0236] Example 2: Transceiver module 701 is used to receive information from intelligent agent network elements;

[0237] The processing module 702 is used to store information of the intelligent agent network element; the intelligent agent network element is a network element that processes communication task information based on an AI / ML model, and the communication task information is used to declare the communication task goal to be achieved.

[0238] Optionally, the information of the agent element includes: the capabilities of the agent element or the rules by which the agent element is used.

[0239] In one possible design, the processing module 702 is used to configure the role type of the intelligent agent network element in the communication task based on the information of the intelligent agent network element.

[0240] Optionally, the role type includes at least one of the following: orchestrating agent network elements, assembling agent network elements, executing agent network elements, connecting agent network elements, or trusted agent network elements.

[0241] Optionally, the task category to which the intelligent agent network element belongs in the communication task can be configured based on the information and role type of the intelligent agent network element.

[0242] In one possible design, the information of the intelligent agent network element is unstructured or semi-structured data.

[0243] Optionally, the information of the agent network element is unstructured data, including information constructed from a self-declared language; or, the information of the agent network element is semi-structured data, including information constructed from a self-declared language and semantic delimiters.

[0244] Optionally, the communication device 700 may further include a storage module that stores programs or instructions. When the transceiver module 701 executes the program or instructions, the communication device 700 can perform the network storage function in the communication method shown in FIG. 5 or FIG. 6.

[0245] It should be understood that the transceiver module 701 can be implemented by a transceiver or transceiver-related circuit components, and can be a transceiver or transceiver unit.

[0246] Furthermore, the communication device 700 can be a network storage function, a chip (system) or other component or assembly disposed in the aforementioned network storage function, or a device containing the network storage function; this application embodiment does not limit this. The technical effects of the communication device 700 can be referred to the technical effects of the communication methods shown in Figures 5 or 6, respectively, and will not be repeated here.

[0247] For example, Figure 8 is a second schematic diagram of the structure of a communication device provided in an embodiment of this application. This communication device can be a first intelligent agent network element, a second intelligent agent network element, or a network storage function; it can also be a chip (system) or other component or assembly that can be disposed in the first intelligent agent network element, the second intelligent agent network element, or the network storage function. As shown in Figure 8, the communication device 800 may include a processor 801. Optionally, the communication device 800 may also include a memory 802 and / or a transceiver 803. The processor 801 is coupled to the memory 802 and the transceiver 803, and may be connected via a communication bus.

[0248] The following section, with reference to Figure 8, provides a detailed description of each component of the communication device 800:

[0249] The processor 801 is the control center of the communication device 800. It can be a single processor or a collective term for multiple processing elements. For example, the processor 801 can be one or more CPUs, an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application, such as one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs).

[0250] Optionally, the processor 801 can perform various functions of the communication device 800 by running or executing software programs stored in the memory 802 and by calling data stored in the memory 802.

[0251] In a specific implementation, as one example, processor 801 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG8.

[0252] In a specific implementation, as one embodiment, the communication device 800 may also include multiple processors, such as processors 801 and 804 shown in FIG. 8. Each of these processors may be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0253] The memory 802 is used to store the software program that executes the solution of this application, and is controlled by the processor 801 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0254] Optionally, the memory 802 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory 802 may be integrated with the processor 801 or may exist independently and be coupled to the processor 801 through the interface circuit of the communication device 800 (not shown in FIG. 8). This application embodiment does not specifically limit this.

[0255] Transceiver 803 is used for communication with other communication devices. For example, if communication device 800 is a first intelligent agent network element, transceiver 803 can be used to communicate with a second intelligent agent network element, or with another first intelligent agent network element. As another example, if communication device 800 is a second intelligent agent network element, transceiver 803 can be used to communicate with a network storage function, or with another intelligent agent network element.

[0256] Optionally, transceiver 803 may include a receiver and a transmitter (not shown separately in Figure 8). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0257] Optionally, the transceiver 803 can be integrated with the processor 801 or exist independently and be coupled to the processor 801 through the interface circuit of the communication device 800 (not shown in FIG8). This application embodiment does not specifically limit this.

[0258] It should be noted that the structure of the communication device 800 shown in Figure 8 does not constitute a limitation on the communication device. The actual communication device may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0259] Furthermore, the technical effects of the communication device 800 can be referred to the technical effects of the communication method described in the above method embodiments, and will not be repeated here.

[0260] It should be understood that the processor in the embodiments of this application can be a CPU, but it can also be other general-purpose processors, DSPs, ASICs, FPGAs, or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc.

[0261] It should also be understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be ROM, programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), EEPROM, or flash memory. Volatile memory can be RAM, which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0262] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0263] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0264] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0265] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0266] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0267] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0268] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0269] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0270] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0271] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or an intelligent network element, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0272] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, Applicable to a first intelligent agent network element, the method includes: Obtain communication task information, which is used to declare the communication task objective to be achieved; The operation corresponding to the communication task target is executed to obtain the execution result; the operation corresponding to the communication task target is determined based on the communication task information.

2. The communication method according to claim 1, characterized in that, The acquisition of communication task information includes: The system receives communication task information from the second intelligent agent network element through a first communication interface, which is an interface for receiving communication task information that declares the communication task target.

3. The communication method according to claim 1 or 2, characterized in that, The operation corresponding to the communication task target includes: Based on artificial intelligence (AI) / machine learning (ML) models, the operations corresponding to the communication task objectives are executed.

4. The communication method according to claim 3, characterized in that, The operation corresponding to the communication task objective based on the AI / ML model includes: The communication task information is processed based on an AI / ML model to obtain the operation corresponding to the communication task objective. Perform the operation corresponding to the communication task objective.

5. The communication method according to any one of claims 1-4, characterized in that, The communication task information is unstructured or semi-structured data.

6. The communication method according to claim 5, characterized in that, The communication task information is unstructured data, including information constructed in a self-declarative language; Alternatively, the communication task information may be semi-structured data, including information constructed from self-declared language and semantic delimiters.

7. A communication method, characterized in that, Applicable to a second intelligent agent network element, the method includes: Obtain communication task information, which is used to declare the communication task objective to be achieved; The communication task information is sent to the first intelligent agent network element.

8. The communication method according to claim 7, characterized in that, Sending the communication task information to the first intelligent agent network element includes: The communication task information is sent to the first intelligent agent network element through a second communication interface, which is an interface used to send communication task information that declares the target of the communication task.

9. The communication method according to claim 7 or 8, characterized in that, The method further includes: Discover the first intelligent agent network element.

10. The communication method according to claim 9, characterized in that, The discovery of the first intelligent agent network element includes: Send communication task information to the network storage function; The system receives response information sent by the network storage function, the response information indicating a first intelligent agent network element, which is a network element in the communication network capable of achieving the communication task objective.

11. The communication method according to claim 10, characterized in that, Sending communication task information to the network storage function includes: The communication task information is sent to the network storage function through a third communication interface, which is an interface used to send communication task information that declares the target of the communication task.

12. The communication method according to any one of claims 1-11, characterized in that, The first intelligent agent network element and the second intelligent agent network element are network elements in a communication network.

13. A communication method, characterized in that, Applicable to network storage functions, the method includes: Receive communication task information from the second intelligent agent network element, wherein the communication task information is used to declare the communication task objective to be achieved; Based on the communication task information, a response message is sent to the second intelligent agent network element. The response message indicates the first intelligent agent network element, which is a network element in the communication network that can realize the communication task target corresponding to the communication task information.

14. The communication method according to claim 13, characterized in that, Sending response information to the second intelligent agent network element according to the communication task information includes: By semantically matching the communication task information with the information of at least one preset intelligent agent network element, a matching result is obtained. The matching result indicates the first intelligent agent network element, and the first intelligent agent network element belongs to the at least one intelligent agent network element. Based on the matching result, a response message is sent to the second intelligent agent network element.

15. The communication method according to claim 14, characterized in that, The step of semantically matching the communication task information with information from at least one preset intelligent agent network element to obtain a matching result includes: The communication task information is semantically matched with the information of at least one preset intelligent agent network element using an artificial intelligence (AI) / machine learning (ML) model to obtain the matching result.

16. The communication method according to claim 14 or 15, characterized in that, The information of the at least one intelligent agent network element includes the role category to which the at least one intelligent agent network element belongs, and the first intelligent agent network element is the intelligent agent network element of the role category among the at least one intelligent agent network elements that can achieve the communication task objective.

17. The communication method according to claim 13, characterized in that, The communication task information is unstructured or semi-structured data.

18. The communication method according to claim 17, characterized in that, The communication task information is unstructured data, including information constructed in a self-declarative language; Alternatively, the communication task information may be semi-structured data, including information constructed from self-declared language and semantic delimiters.

19. A communication method, characterized in that, Applicable to network storage functions, the method includes: Receive information from intelligent agent network elements; Save the information of the intelligent agent network element; The intelligent agent network element is a network element that processes communication task information based on an artificial intelligence (AI) / machine learning (ML) model. The communication task information is used to declare the communication task objectives to be achieved.

20. The communication method according to claim 19, characterized in that, The information of the agent network element includes: the capabilities of the agent network element or the rules by which the agent network element is used.

21. The communication method according to claim 19 or 20, characterized in that, The method further includes: Based on the information of the intelligent agent network element, configure the role type of the intelligent agent network element in the communication task.

22. The communication method according to claim 21, characterized in that, The role type includes at least one of the following: orchestrating intelligent agent network elements, assembling intelligent agent network elements, executing intelligent agent network elements, connecting intelligent agent network elements, or trusted intelligent agent network elements.

23. The communication method according to claim 22, characterized in that, The method further includes: Based on the information of the intelligent agent network element and the role type, configure the task category to which the intelligent agent network element belongs in the communication task.

24. The communication method according to claim 19, characterized in that, The information of the intelligent agent network element is unstructured data or semi-structured data.

25. The communication method according to claim 24, characterized in that, The information of the intelligent agent network element is unstructured data, including information constructed using a self-declarative language. Alternatively, the information of the intelligent agent network element may be semi-structured data, including information constructed from self-declared language and semantic delimiters.

26. A communication device, characterized in that, The communication device includes a processor and a transceiver, the transceiver being used for information exchange between the communication device and other communication devices, and the processor executing program instructions to perform the method as described in any one of claims 1-25.

27. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program or instructions that, when executed on a computer, cause the computer to perform the method as described in any one of claims 1-25.

28. A computer program product, characterized in that, The computer program product includes: a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-25.

Images