Communication method and communication apparatus

Abstract

A communication method, comprising: a first entity generating a prompt on the basis of a user intent, and sending the prompt to an AI model entity, such that the AI model entity can determine a network topology on the basis of the received prompt; the AI model entity sending the network topology to the first entity; the first entity sending to a second entity information of the network topology and task requirement information; and the second entity creating a first network instance on the basis of the information of the network topology and the task requirement information, wherein the creation of the first network instance comprises at least one of the deployment of network functions, the configuration of an access network device and the configuration of a terminal. A system, which comprises a first entity, an AI model entity and a second entity and is deployed in a wireless network, can flexibly orchestrate network functions and / or application functions on the basis of user intents, so as to provide customized network services for users, thereby improving the intelligence level of the wireless network.

Description

A communication method and communication device

[0001] This application claims priority to Chinese Patent Application No. 202410517724.7, filed on April 24, 2024, entitled "A Communication Method and Communication Device", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of communications, specifically to a communication method and a communication device. Background Technology

[0003] In fifth-generation (5G) communication systems, network slicing technology has emerged to meet the diverse quality of service (QoS) requirements of different industries, users, and services. For example, enhanced mobile broadband (eMBB) services such as live streaming and video backhaul have high transmission rate requirements; massive machine-type communication (mMTC) services such as smart agriculture and smart meter reading require the network to support massive device access and frequent transmission of numerous small packets; and ultra-reliable low-latency communication (uRLLC) services such as vehicle-to-everything (V2X) and industrial control require millisecond-level latency and high reliability.

[0004] Network slicing provides multiple dedicated, virtualized, and isolated logical networks on the same shared infrastructure, with each logical network serving a specific business type or industry user. Each network slice can flexibly define its own logical topology, service level agreement (SLA) requirements, reliability, and security levels to meet the differentiated needs of different businesses or users.

[0005] However, current 5G network slicing primarily provides differentiated network connectivity capabilities, lacking the ability to customize business logic. The configuration and maintenance of the entire sliced ​​network require corresponding operational costs, and its level of intelligence is insufficient. Therefore, improving the intelligence level of the network has become an urgent problem to be solved. Summary of the Invention

[0006] This application provides a communication method aimed at improving the intelligence level of a network.

[0007] Firstly, a communication method is provided, comprising: a first entity sending a prompt to an artificial intelligence (AI) model entity, the prompt being generated based on user intent; the AI ​​model entity determining a network topology based on the prompt and sending the network topology to the first entity; the first entity receiving the network topology and sending network topology information and task requirement information to a second entity; and the second entity creating a first network instance based on the network topology information and task requirement information, wherein creating the first network instance includes at least one of the deployment of network functions, configuration of access network devices, and configuration of terminals, and the task requirement information is used to indicate the quality of service (QoS) requirements of the first network instance.

[0008] Based on the above technical solution, the process of the second entity creating a network instance according to the received network topology information and task requirement information includes the deployment of network functions, as well as the configuration of access network devices and terminals in the wireless network. The network topology is obtained by the AI ​​model entity orchestrating network functions and / or application functions based on the prompt input by the first entity, and the prompt is generated based on user intent. In other words, the system deployed on the wireless network can flexibly orchestrate network functions and / or application functions based on user intent, providing customized network services to users and improving the intelligence level of the wireless network.

[0009] In one possible design, the communication system described above further includes a third entity, and the method further includes: a first entity obtaining auxiliary information related to the user's intent from the third entity based on the user's intent. The first entity generates the prompt based on the user's intent and the auxiliary information, wherein the auxiliary information includes interaction data of at least one network instance runtime environment and / or context information of network functions.

[0010] Based on the above technical solution, the first entity can obtain auxiliary information related to the user's intent from the third entity according to the user's intent. Thus, in the process of generating the prompt, not only the user's intent but also the obtained auxiliary information is taken into account, in order to improve the accuracy of the generated prompt.

[0011] In another possible design, the first entity obtains auxiliary information related to the user's intent from the third entity based on the user's intent. This includes: the first entity sending a first message to the third entity through a first interface, the first message being used to obtain auxiliary information related to the user's intent from the third entity. The first message includes at least one of the following: information about the user's intent, a relevance requirement, or a time requirement, wherein the relevance requirement is used to indicate the relevance between the user's intent and the auxiliary information, and the relevance requirement may be greater than a given relevance threshold; the time requirement is used to identify the generation time of the auxiliary information, and the time requirement may be no later than or no earlier than a given time threshold. The first entity receives the auxiliary information from the third entity through the first interface.

[0012] Based on the above technical solution, the first entity and the third entity can transmit data and / or signaling through the first interface. Furthermore, the method by which the first entity obtains data from the third entity can be standardized. For example, the type of data the first entity can obtain from the third entity, the relevance requirements between the obtained data and the user intent, and the time requirements between the obtained data and the user intent can all be standardized.

[0013] In another possible design, the first entity sends the network topology information and task requirement information to the second entity, including: the first entity sending a second message to the second entity through a second interface, the second message including the network topology information and the task requirement information, wherein the network topology information includes the identifier of each function in at least one function included in the network topology and the association relationship between the at least one function.

[0014] Based on the above technical solution, the first entity and the second entity can transmit data and / or signaling through the second interface. Furthermore, the network topology information provided by the first entity to the second entity can be standardized. For example, the network topology information provided by the first entity to the second entity includes function identifiers and the connection relationships between functions.

[0015] In another possible design, the first entity sends a prompt to the AI ​​model entity, including: the first entity sending a third message to the AI ​​model entity through a third interface. The third message contains instructions, extended data, or requirements for generating results. The instructions are the user intent, the extended data is auxiliary information, and the requirements for generating results are the requirements for the results generated by the AI ​​model entity, such as inference time, training accuracy, and data size. Optionally, the third message may also include an example, which provides a standard solution for the AI ​​model entity to refer to.

[0016] In another possible design, the AI ​​model entity sending the network topology to the first entity includes: the AI ​​model entity sending a fourth message to the first entity through a third interface, the fourth message including the name of at least one function in the network topology, the connection relationship between at least one function, the data content of the input and output of each of the at least one function, and the input parameter configuration of each of the at least one function.

[0017] Based on the above technical solution, the first entity and the third entity can transmit data and / or signaling through a third interface. Furthermore, the method by which the first entity and the third entity transmit data can be standardized.

[0018] In another possible design, the second entity creates a first network instance based on the network topology information and the task requirement information, including: the second entity determines configuration parameters of at least one function included in the network topology based on the task requirement information, wherein the at least one function includes at least one network function and / or at least one application function.

[0019] Secondly, a communication method is provided. This method can be executed by a first entity. Unless otherwise specified, the "first entity" in this application can refer to a network device (e.g., an agent device or agent module), a component within the network device (e.g., a processor, chip, or chip system), or a logical module or software capable of implementing all or part of the functions of the network device. For ease of description, the following description uses the execution by the first entity as an example.

[0020] The communication method includes: sending a prompt to an AI model entity, the prompt being generated based on user intent; and receiving a network topology from the AI ​​model entity, the network topology being generated based on the prompt. The network topology is used to create a first network instance, and creating the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals.

[0021] In one possible design, the method further includes: obtaining auxiliary information related to the user intent from a third entity based on the user intent; generating the prompt based on the user intent and the auxiliary information, wherein the auxiliary information includes interaction data of at least one network instance runtime environment and / or context information of network functions.

[0022] In another possible design, obtaining auxiliary information related to the user intent from a third entity based on the user intent includes: sending a first message to the third entity via a first interface, the first message being used to obtain auxiliary information related to the user intent from the third entity. The first message includes at least one of the following: information about the user intent, a relevance requirement, or a time requirement, wherein the relevance requirement indicates the relevance between the user intent and the auxiliary information, and the relevance requirement may be greater than a given relevance threshold; the time requirement identifies the generation time of the auxiliary information, and the time requirement may be no later than or no earlier than a given time threshold. The auxiliary information is received from the third entity via the first interface.

[0023] In another possible design, the method further includes sending network topology information and task requirement information to the second entity, the task requirement information being used to indicate the Quality of Service (QoS) requirements of the first network instance.

[0024] In another possible design, sending the network topology information and task requirement information to the second entity includes: sending a second message to the second entity through a second interface, the second message including the network topology information and the task requirement information, wherein the network topology information includes the identifier of each function in at least one function included in the network topology and the association relationship between the at least one function.

[0025] In another possible design, sending a prompt to the AI ​​model entity includes: sending a third message to the AI ​​model entity via a third interface. The third message includes instructions, extended data, or a result generation requirement. The instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the result generation requirement indicates the requirements that the AI ​​model entity must meet in generating the result, such as inference time, training accuracy, and data size. Optionally, the third message may also include an example, which provides a standard solution for the AI ​​model entity to reference.

[0026] In another possible design, receiving the network topology from the AI ​​model entity includes: receiving a fourth message from the AI ​​model entity via a third interface, the fourth message including the name of at least one function in the network topology, the connection relationship between the at least one function, the input and output data content of each function, or the input parameter configuration of each function.

[0027] The technical effects of the methods shown in the second aspect and its possible designs above can be referred to the technical effects in the first aspect and its possible designs.

[0028] Thirdly, a communication method is provided. This method can be executed by an AI model entity. Unless otherwise specified, "AI model entity" in this application can refer to the AI ​​model entity itself (e.g., a large model module), a component within the AI ​​model entity (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the AI ​​model entity. For ease of description, the following explanation uses the execution by an AI model entity as an example.

[0029] The communication method includes: receiving a prompt from a first entity, the prompt being generated based on a user intent; determining a network topology based on the prompt; and sending the network topology to the first entity, wherein the network topology is used to create a first network instance, the creation of the first network instance including at least one of network function deployment, access network device configuration, and terminal configuration.

[0030] In one possible design, determining the network topology based on the prompt includes: determining a thought chain based on the prompt, the thought chain including at least one step required to achieve the user intent; and matching at least one network function and / or application function to the at least one step based on background knowledge.

[0031] In another possible design, the network function includes at least one of the following: connectivity, computing, perception, or artificial intelligence (AI) function; the application function includes at least one of the following: image classification, image statistics, environment modeling, path planning, target recognition, or text generation.

[0032] In another possible design, receiving the prompt from the first entity includes: receiving a third message from the first entity via a third interface. This third message includes instructions, extended data, or a result generation requirement. The instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the result generation requirement indicates the requirements that the AI ​​model entity must meet when generating the result, such as inference time, training accuracy, and data size. Optionally, the third message may also include an example, providing a standard solution for the AI ​​model entity to reference.

[0033] In another possible design, sending the network topology to the first entity includes: sending a fourth message to the first entity via a third interface, the fourth message including the name of at least one function in the network topology, the connection relationship between the at least one function, the input and output data content of each function, or the input parameter configuration of each function.

[0034] The technical effects of the methods shown in the third aspect and its possible designs above can be referred to the technical effects in the first aspect and its possible designs.

[0035] Fourthly, a communication method is provided. This method can be executed by a second entity. Unless otherwise specified, the "second entity" in this application can refer to the second entity itself (e.g., an actor module), a component within the second entity (e.g., a processor, chip, or chip system), or a logic module or software capable of implementing all or part of the functions of the second entity. For ease of description, the following explanation uses the execution of a second entity as an example.

[0036] The communication method includes: receiving network topology information and task requirement information from a first entity, wherein the network topology is determined based on a prompt and the prompt is generated based on user intent; and creating a first network instance based on the network topology information and the task requirement information, wherein creating the first network instance includes at least one of network function deployment, access network device configuration, and terminal configuration, and the task requirement information is used to indicate the Quality of Service (QoS) requirements of the first network instance.

[0037] In one possible design, creating a first network instance based on the network topology information and the task requirement information includes: determining configuration parameters for at least one function included in the network topology based on the task requirement information, wherein the at least one function includes at least one network function and / or at least one application function.

[0038] In another possible design, the method further includes: deleting and / or updating the first network instance.

[0039] In another possible design, deleting the first network instance includes: reclaiming the computing resources corresponding to the first network instance and deleting the identifier of the first network instance.

[0040] In another possible design, updating the first network instance includes: receiving update information from the first entity, the update information including an identifier of the first network instance, the update information indicating that the first network instance should be updated; or, detecting an event that triggers the updating of the first network instance, the event including at least one of the following: network function and / or application function failure, the terminal device moving, the access network device moving, the transmission link quality between the terminal device and the access network device deteriorating, or the access network device experiencing service congestion.

[0041] In another possible design, the method further includes sending the runtime data of the first network instance to a third entity.

[0042] In another possible design, receiving network topology information and task requirement information from the first entity includes: receiving a second message from the first entity through a second interface, the second message including the network topology information and the task requirement information, wherein the network topology information includes the identifier of each function in at least one function included in the network topology and the association relationship between the at least one function.

[0043] The technical effects of the methods shown in the fourth aspect and its possible designs above can be referred to the technical effects in the first aspect and its possible designs.

[0044] Fifthly, a communication method is provided. This method can be applied to a terminal device, which may be, for example, a terminal equipment or a communication module in a terminal equipment, or a circuit or chip in a terminal equipment responsible for communication functions (such as a modem chip, also known as a baseband chip, or a system-on-chip (SoC) chip containing a modem core or a system-in-package (SIP) chip).

[0045] In this method, the terminal device receives configuration information indicating the terminal's configuration during the creation of a first network instance. The terminal device performs configuration based on the configuration information, wherein creating the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of the terminal. The first network instance is created based on network topology information and task requirement information. The network topology is determined based on a prompt, which is generated based on user intent. The task requirement information indicates the QoS requirements of the first network instance.

[0046] In one possible design, the terminal device sends the aforementioned user intent to a first entity, enabling the first entity to generate a prompt based on the user intent and provide it to an AI model entity. The AI ​​model entity then determines the network topology based on the prompt. The AI ​​model entity provides the determined network topology to the first entity, which in turn sends the network topology information and task requirement information to a second entity. The second entity then creates a first network instance based on the network topology information and task requirement information. This enables flexible orchestration of network functions and / or application functions based on user intent, providing customized network services to users and improving the intelligence level of the wireless network.

[0047] The technical effects of the methods shown in the fifth aspect above and its possible designs can be referred to the technical effects in the first aspect and its possible designs.

[0048] Sixthly, this application provides a communication device that has the functions of implementing the second to fifth aspects described above. For example, the communication device includes modules, units, or means corresponding to the operations involved in the second to fifth aspects described above. The modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0049] In a seventh aspect, this application provides a communication device comprising at least one processor coupled to a memory. The memory stores part or all of a computer program or instructions necessary for implementing the functions described in the first aspect. The at least one processor is capable of executing the computer program or instructions, which, when executed, cause the communication device to implement the methods in any possible design or implementation of the second to fifth aspects described above.

[0050] In one possible design, the communication device may further include an interface circuit, wherein the processor is used to communicate with other devices or components through the interface circuit.

[0051] In one possible design, the communication device may further include the memory. Optionally, the memory and processor are integrated together.

[0052] The aforementioned communication device may be a terminal in the fifth aspect, or a communication module in a terminal, or a chip in a terminal that is responsible for communication functions, such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module.

[0053] Eighthly, this application provides a chip, which includes a processor and a communication interface. The processor reads instructions through the communication interface and executes the method provided by any of the implementations of the first to fifth aspects described above.

[0054] Ninthly, this application provides a communication system including a first entity for performing the method in the second aspect, an AI model entity for performing the method in the third aspect, and a second entity for performing the method in the fourth aspect.

[0055] Optionally, the communication system also includes a terminal for performing the methods in the fifth aspect.

[0056] In a tenth aspect, this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to fifth aspects described above.

[0057] In one aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to fifth aspects described above. Attached Figure Description

[0058] Figure 1 is a schematic diagram of a communication system applicable to this application.

[0059] Figure 2 is a schematic diagram of the AI ​​agent.

[0060] Figure 3 is a schematic diagram of a network slice.

[0061] Figure 4 is a schematic diagram of a network slice management architecture.

[0062] Figure 5 is a schematic flowchart of a communication method provided in this application.

[0063] Figure 6 is a schematic diagram of a tool library provided in this application.

[0064] Figure 7 is a schematic diagram of a communication system provided in this application.

[0065] Figure 8 is a schematic diagram of the communication interface between various functional entities in a communication system provided in this application.

[0066] Figure 9 is a schematic block diagram of the communication device 10 provided in an embodiment of this application.

[0067] Figure 10 is a schematic diagram of another communication device 20 provided in an embodiment of this application. Detailed Implementation

[0068] To facilitate understanding of the embodiments of this application, the following points will be explained first.

[0069] First, in this application, "for indicating" can include both direct and indirect indication. When describing an indication message as indicating A, it can include whether the indication message directly indicates A or indirectly indicates A, but does not necessarily mean that the indication message carries A.

[0070] The information indicated by the instruction is called the information to be instructed. In the specific implementation process, there are many ways to indicate the information to be instructed, such as, but not limited to, directly indicating the information to be instructed, such as the information to be instructed 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 instructed. 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 instruction of specific information can be achieved by using a pre-agreed (e.g., protocol-defined) arrangement of various pieces of information, thereby reducing instruction overhead to some extent. At the same time, common parts of various pieces of information can be identified and indicated uniformly to reduce the instruction overhead caused by individually indicating the same information.

[0071] Second, in this application, "at least one" refers to one or more, and "more than one" refers to two or more (including two). Furthermore, in the embodiments of this application, "first," "second," and various numerical designations (e.g., "#1," "#2," etc.) are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application. The sequence numbers of the processes below do not imply an 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. It should be understood that the objects described in this way can be interchanged where appropriate to describe solutions other than those in the embodiments of this application. Moreover, in the embodiments of this application, terms such as "S510" are merely identifiers for descriptive convenience and do not limit the order of execution steps.

[0072] Third, in the embodiments of this application, the words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design options. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0073] Fourth, the term "storage" in the embodiments of this application can refer to storage in one or more memories. These memories can be separate installations or integrated into an encoder, decoder, processor, or communication device. Alternatively, some memories can be separately installed, while others are integrated into the processor or communication device. The type of memory can be any form of storage medium, and this application does not limit this.

[0074] Fifth, in the implementation of this application, "protocol" may refer to standard protocols in the field of communications, such as the NR protocol and related protocols applied in future communication systems, and this application does not limit it.

[0075] Sixth, in the embodiments of this application, the terms "of", "corresponding (relevant)", "corresponding", and "associate" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, their intended meanings are consistent.

[0076] Seventh, in the embodiments of this application, "under the circumstances", "when", and "if" can sometimes be used interchangeably. It should be noted that when the distinction is not emphasized, their intended meanings are consistent.

[0077] Eighth, 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. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0078] Ninth, in this article, "message", "information", or "information element (IE)" can be used interchangeably. There are no restrictions on the name of the message or information, as long as it can achieve the corresponding function.

[0079] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0080] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, 5th Generation (5G) systems such as New Radio (NR), Future Communication Systems, and other communication systems that evolve after 5G; Vehicle-to-X (V2X) connectivity, where V2X can include vehicle-to-network (V2N), vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P), etc.; Long Term Evolution-Vehicle (LTE-V) communication technology; Vehicle-to-Everything (V2X); Machine-Type Communication (MTC); Internet of Things (IoT); Long Term Evolution-Machine (LTE-M) communication technology; and Machine-to-Machine (MTC) communication technology. Machine (M2M), etc.

[0081] Furthermore, the embodiments of this application are applicable to both homogeneous and heterogeneous network scenarios, and there are no restrictions on the transmission points. They can be applied to systems such as multi-point collaborative transmission between macro base stations, micro base stations, and macro base stations. The embodiments of this application are applicable to both low-frequency scenarios (sub 6 GHz) and high-frequency scenarios (above 6 GHz), terahertz, optical communication, etc.

[0082] Figure 1 is a schematic diagram of a communication system applicable to this application. As shown in Figure 1, the communication system 100 includes at least one network device, which may be an access network device, such as network device 111 and network device 112 shown in Figure 1; and / or, the network device may be a core network (CN) device, such as core network device 130 shown in Figure 1; the communication system 100 may also include at least one terminal device, such as at least one of terminal device 121, terminal device 122, and terminal device 123 shown in Figure 1. In this communication system, the network device and the terminal device can communicate via a wireless link, thereby exchanging information. It is understood that the network device and the terminal device may also be referred to as communication equipment or communication apparatus.

[0083] Access network equipment can be a network-side device with wireless transceiver capabilities. It can be a device within a radio access network (RAN) that provides wireless communication functionality to terminal devices, referred to as RAN equipment. RAN can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as a 5G mobile communication system, or a future-oriented evolution system. RAN can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. For example, this access network equipment can be a base station, an evolved NodeB (eNodeB), a next-generation NodeB (gNB) in a 5G mobile communication system, a 3GPP subsequent evolution base station, a transmission reception point (TRP), an access node, a wireless relay node, or a wireless backhaul node in a WiFi system. In communication systems employing different radio access technologies (RATs), the names of devices with base station functionality may differ. For example, in an LTE system, it may be called an eNB or eNodeB, and in a 5G or NR system, it may be called a gNB. This application does not limit the specific name of the base station. Access network equipment may include one or more co-located or non-co-located transmit / receive points. Furthermore, access network equipment may include at least one of the following: one or more central units (CU), one or more distributed units (DU), and one or more radio units (RU). In different systems, CU (or CU-CP and CU-UP), DU, or RU may also have different names, but those skilled in the art will understand their meaning. For example, in an open RAN (ORAN) system, CU may also be called O-CU (open CU), DU may also be called O-DU (open DU), CU-CP may also be called O-CU-CP, CU-UP may also be called O-CU-UP, and RU may also be called O-RU. Any of the units among CU (or CU-CP, CU-UP), DU, and RU in this application may be implemented through software modules, hardware modules, or a combination of software and hardware modules.For example, the functionality of a CU can be implemented by one entity or different entities. For instance, the CU's functionality can be further divided, separating the control plane and user plane and implementing them through different entities: a control plane CU entity (i.e., the CU-CP entity) and a user plane CU entity (i.e., the CU-UP entity). The CU-CP and CU-UP entities can be coupled with a DU to jointly complete the access network device's functionality. For example, the CU is responsible for handling non-real-time protocols and services, implementing the functions of the radio resource control (RRC) and packet data convergence protocol (PDCP) layers. The DU is responsible for handling physical layer protocols and real-time services, implementing the functions of the radio link control (RLC) layer, media access control (MAC) layer, and physical (PHY) layer. In this way, some functions of the wireless access network device can be implemented through multiple network function entities. These network function entities can be network elements in hardware devices, software functions running on dedicated hardware, or virtualized functions instantiated on a platform (e.g., a cloud platform). The access network device can also include an active antenna unit (AAU). The AAU implements some physical layer processing functions, radio frequency processing, and related functions of the active antenna. Since RRC layer information ultimately becomes PHY layer information, or is derived from PHY layer information, in this architecture, higher-layer signaling, such as RRC layer signaling, can also be considered as being sent by the DU, or by the DU+AAU. It is understood that access network equipment can be one or more of the following: CU nodes, DU nodes, and AAU nodes. Furthermore, the CU can be classified as an access network device in the radio access network (RAN), or as an access network device in the core network (CN); this application does not limit this. For example, in V2X technology, access network equipment can be a roadside unit (RSU). Multiple access network devices in a communication system can be base stations of the same type or different types. Base stations can communicate with terminal devices directly, or they can communicate with terminal devices through relay stations. In this embodiment, the device for implementing the access network device function can be the access network device itself, or it can be a device that supports the access network device in implementing the function, such as a chip system or a combination of devices or components that can implement the access network device function. This device can be installed in the access network device. In this embodiment, the chip system can be composed of chips, or it can include chips and other discrete devices.

[0084] Terminal equipment can be any device or module that accesses the aforementioned communication system and possesses corresponding communication functions. Terminal equipment can also be referred to as user equipment (UE), terminal, user device, access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal device, wireless communication equipment, user agent, or user device. Terminals typically contain communication modules, circuits, or chips that perform the corresponding communication functions. The terminal may also be configured with program instructions for performing these communication functions.

[0085] For example, the terminal in this application embodiment can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer, a drone, a computer with wireless transceiver capabilities, a machine-type communication (MTC) terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a point-of-sale (POS) machine, customer-premises equipment (CPE), a light user equipment (UE), a reduced capability UE (REDCAP UE), a wearable device (e.g., a smartwatch, smart bracelet, pedometer, smart glasses), an Internet of Things (IoT) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, or a wireless terminal in a smart home. Wireless terminals in the home (such as game consoles, smart TVs, smart speakers, smart refrigerators, and fitness equipment), transportation vehicles with wireless communication capabilities, communication modules, roadside units (RSUs) with terminal functions, and flying equipment (such as smart robots, hot air balloons, drones, and airplanes). Terminal equipment can also be vehicle devices, such as complete vehicle devices, vehicle-mounted modules, vehicle-mounted chips, on-board units (OBUs), or telematics boxes (T-BOXs).

[0086] The main functions of core network equipment are to provide user connectivity, manage users, and carry out service delivery, while also providing an interface to external networks as the bearer network.

[0087] For example, a core network device may include one or more of the following functional network elements:

[0088] Application function (AF) network elements, access and mobility management function (AMF) network elements, session management function (SMF) network elements, network slice selection function (NSSF) network elements, unified data management (UDM) network elements, network function repository function (NRF) network elements, etc.

[0089] Among them, AF is used to provide application layer information; AMF is responsible for access control and mobility management of terminal equipment 110 accessing the operator's network; SMF is responsible for managing the terminal's protocol data unit (PDU) sessions; NSSF is responsible for determining network slice instances and selecting AMFs, etc.; UDM is responsible for storing information of subscribed users in the operator's network; NRF can be used to maintain real-time information on network functions and services in the network. It should be understood that core network equipment may also include other network elements, which will not be elaborated here.

[0090] In addition, unless otherwise specified, the core network equipment in this application may also be other equipment capable of performing the corresponding functions. For example, an AI model entity, memory module, execution module, or agent module with an AI model deployed thereon.

[0091] It is understood that the aforementioned network elements or functions can be physical entities in hardware devices, software instances running on dedicated hardware, or virtualization functions instantiated on shared platforms (e.g., cloud platforms). This application does not impose any limitations on the specific form or name of the aforementioned network elements.

[0092] It should also be understood that the aforementioned AF, AMF, NSSF, UDM, or NRF can be understood as network elements in the core network used to implement different functions, such as network slices that can be combined as needed. These core network elements can be independent devices or integrated into the same device to implement different functions. This application does not limit the specific form of the aforementioned network elements.

[0093] It should also be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks. For example, in future communication networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0094] Access network equipment, terminal equipment, and core network equipment can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on aircraft, balloons, and satellites. This application embodiment does not limit the scenario in which the network equipment, terminal equipment, and core network equipment are located.

[0095] To facilitate understanding of the embodiments of this application, the basic concepts involved in this application will be explained first.

[0096] 1. Convergence of Communications and Artificial Intelligence (AI): The International Telecommunication Union – Radiocommunication Sector (ITU-R) vision for future communications describes new service scenarios that future communication networks need to support, such as immersive communications, smart industry, and digital healthcare. These new services have diverse performance requirements, significantly increasing the complexity of network functions and the difficulty of management and configuration. To better serve these new services, future communication networks need strong on-demand customization capabilities to configure various functions and resources in a more flexible and dynamic manner. With the steady development and rapid popularization of AI technology, its introduction can help achieve this goal.

[0097] This leads to the fundamental concept of the convergence of communication and AI: network AI. Network AI aims to provide a complete AI environment and services within a network through a unified architectural design. Optionally, the future convergence of communication and AI may manifest as the integration of communication with large-scale models.

[0098] 2. Large Model Techniques: Large models refer to neural network models containing an extremely large number of parameters (usually over one billion), and have the following characteristics:

[0099] 1) Huge scale: Large models contain billions of parameters, and their size can reach hundreds of gigabytes (GB) or even larger. This huge model scale provides powerful expressive and learning capabilities.

[0100] 2) Multi-task learning: Large models typically learn multiple different natural language processing (NLP) tasks, such as machine translation, text summarization, or question answering systems. This allows the model to learn a broader and more generalized language understanding ability.

[0101] 3) Powerful computing resources: Training large models typically requires hundreds or even thousands of graphics processing units (GPUs) and a significant amount of time, usually ranging from weeks to months. This can accelerate the training process while retaining the ability to train large models.

[0102] 4) Abundant data: Large models require a large amount of data for training, and a large amount of data can leverage the advantages of the parameter scale of large models.

[0103] Large models are widely used in the field of natural language processing (NLP) and are transforming NLP tasks, giving rise to more powerful and intelligent language technologies. Large models are a key direction in AI development. They also excel in various NLP tasks, such as text classification, sentiment analysis, summarization, and translation. Furthermore, large models can be used in multiple application areas, including automated writing, chatbots, virtual assistants, voice assistants, and automated translation.

[0104] It should be understood that the application of large-scale models in networks requires a series of supporting peripheral functions to truly realize their potential. This system engineering can be called an AI Agent. The following is a brief explanation of AI Agents.

[0105] 3. AI Agent: As shown in Figure 2, in an autonomous agent system supported by a large language model (LLM), the LLM acts as the brain of the agent, supplemented by several key components:

[0106] 1) Planning, including but not limited to:

[0107] Sub-goal decomposition: Agents break down large tasks into smaller, manageable sub-goals, enabling them to handle complex tasks more efficiently. For example, by instructing the model to "think step by step" through a chain of thoughts (CoT), more testing time is used to compute the breakdown of difficult tasks into smaller, simpler steps. CoT transforms large tasks into multiple manageable tasks and elucidates the explanation of the model's thought process.

[0108] Reflection and Improvement: Intelligent agents can engage in self-criticism and self-reflection on past behaviors, learn from mistakes, and improve future steps, thereby enhancing the quality of the final result.

[0109] 2) Memory, also known as storage, includes, but is not limited to:

[0110] Short-term memory: Learning by utilizing the short-term memory of models.

[0111] Long-term memory: Provides agents with the ability to retain and recall (unlimited) information for a long time, usually by utilizing external vector storage and fast retrieval.

[0112] 3) Tool usage, including but not limited to:

[0113] The agent obtains additional information missing from the model weights by calling external application programming interfaces (APIs), including current information, code execution capabilities, and access to proprietary information sources.

[0114] 4) Task execution (action): The model performs a specific task and records the results.

[0115] 4. Network slicing technology: In the 5G era, in order to meet the different service quality requirements of different industries, users or services, such as eMBB services such as live streaming and video backhaul, which have high requirements for transmission rate, mMTC services such as smart agriculture and smart meter reading, which require the network to support massive device access and frequent transmission of a large number of small packets, and uRLLC services such as vehicle networking and industrial control, which require millisecond-level latency and high reliability, network slicing technology has emerged.

[0116] As shown in Figure 3, network slicing provides multiple dedicated, virtualized, and isolated logical networks on the same shared infrastructure. Each logical network serves a specific business type or industry user (e.g., eMBB applications, mMTC applications, uRLLC applications, etc.). Each network slice (e.g., network slice 1, network slice 2, ..., network slice n) can flexibly define its own logical topology, SLA requirements, reliability, and security levels to meet the differentiated needs of different services or users.

[0117] 5. Network Slice Management Architecture: Figure 4 illustrates the three-layer network slice management architecture. The Communication Service Management Function (CSMF) is responsible for converting relevant service requirements into slice-related requirements (such as SLAs) and then sending them to the Network Slice Management Function (NSMF). The NSMF manages network slice instances and derives slice subnet instance requirements from these requirements before sending them to the Network Slice Subnet Management Function (NSSMF).

[0118] The NSSMF includes the access network NSSMF (AN-NSSMF), the transport network NSSMF (TN-NSSMF), and the core network NSSMF (CN-NSSMF). The AN-NSSMF is responsible for managing network slice subnet instances within each domain of the RAN network; the TN-NSSMF is responsible for managing network slice subnet instances within each domain of the TN network; and the CN-NSSMF is responsible for managing network slice subnet instances within each domain of the CN network.

[0119] When a terminal wants to access a network slice, it includes requested network slice selection assistance information (requested NSSAI) in its request message to the base station. The base station selects an initial AMF (Application Service Provider). The initial AMF queries the UDM (User Dedicated Provider) for the terminal's subscribed NSSAI and compares the intersection of the requested NSSAI and the subscribed NSSAI to obtain the NSSAI that the terminal is allowed to access. Then, the initial AMF checks whether its configured NSSAI includes the NSSAI that the terminal is allowed to access. If not, the initial AMF does not support the slice and AMF reselection is required. The initial AMF sends the terminal's subscribed NSSAI, requested NSSAI, and terminal location to the NSSF (Network Service Provider Separator). The NSSF selects a target AMF that can support the slice and returns the target AMF information and NRF (Network Provider Recognition) identifier to the initial AMF. The initial AMF obtains the target AMF's IP address from the NRF and sends the terminal's request to the target AMF, which then completes the terminal's access.

[0120] 6. Prompt: In large AI models, the primary role of a prompt is to provide the AI ​​model with contextual information about the input and the model's parameters. When training supervised or unsupervised learning models, prompts help the model better understand the intent of the input and respond accordingly. Furthermore, prompts can improve the interpretability and accessibility of the model.

[0121] In layman's terms, a prompt is to provide an AI model entity with a "hint" or "guidance" to help the AI ​​model entity better understand and complete the task.

[0122] 7. AI Model Entity: This entity can perform some or all AI-related operations. For example, an AI model is deployed within this entity. The AI ​​model entity can also be referred to as an AI node, AI device, AI entity, AI module, or AI unit, etc. An AI model entity can be considered a specific method for implementing AI functions. It represents the mapping relationship or function between the model's input and output. AI functions may include one or more of the following: data collection, model training (or model learning), model information dissemination, model inference (or model reasoning, inference, or prediction, etc.), model monitoring or model validation, or inference result dissemination, etc. AI functions can also be referred to as AI (related) operations or AI-related functions.

[0123] The AI ​​module is used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or bias in the activation function), input parameters (e.g., type and / or dimension of input parameters), or output parameters (e.g., type and / or dimension of output parameters). The bias in the activation function can also be referred to as the neural network bias.

[0124] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0125] The preceding text, with reference to Figure 1, briefly introduced the application scenarios of the communication method provided in this application embodiment, and also introduced the basic concepts that may be involved in this application embodiment. Within these basic concepts, Figures 3 and 4 were used to introduce 5G network slicing technology. As can be seen from the above, 5G network slicing mainly provides differentiated network connectivity capabilities, lacking the ability to customize business logic. Furthermore, the customization of sliced ​​networks is very complex, requiring users to configure network parameters according to their needs, which is too difficult. The configuration and maintenance of the entire sliced ​​network requires corresponding maintenance costs, and its level of intelligence is insufficient.

[0126] This application provides a communication method that can be applied to the communication system shown in Figure 1, with the aim of incorporating the concept of AI Agent into wireless networks, flexibly orchestrating network functions and / or application functions based on user intent, providing users with customized network services, and improving user experience.

[0127] It should be understood that the embodiments shown below do not particularly limit the specific structure of the execution subject of the method provided in the embodiments of this application, as long as it is possible to communicate according to the method provided in the embodiments of this application by running a program that records the code of the method provided in the embodiments of this application.

[0128] For example, the execution subject of the method provided in the embodiments of this application can be an entity. Unless otherwise specified, the "entity" in this application can refer to the device itself (e.g., agent module, memory module, actor module, or AI model entity), or a component in the device (e.g., processor, chip, or chip system), or a logic module or software that can implement all or part of the device functions.

[0129] Figure 5 is a schematic flowchart of a communication method provided in this application.

[0130] S510, the first entity sends a prompt to the AI ​​model entity, and the AI ​​model entity receives the prompt from the first entity accordingly.

[0131] For example, the first entity may also be referred to as a first functional entity, a first independent unit, a first logical module, or a controller, etc. For instance, the first entity may be an agent module, capable of coordinating other components (such as a memory module, an actor module, or an AI model entity) to create a corresponding network instance based on user intent. This application does not impose any limitations on the name of the first entity, as long as it can achieve the corresponding function.

[0132] Furthermore, the AI ​​model entity in this embodiment is a module capable of determining network topology based on a prompt, and can also be referred to as an AI module, AI network element, large model, etc. For example, the AI ​​model entity in this embodiment can be a large model, capable of orchestrating network functions and / or application functions, and generating network function topology. This application does not impose any limitations on the name of the AI ​​model entity, as long as it can achieve the corresponding function.

[0133] Specifically, the prompt is generated based on the user's intent, and includes information related to that intent. For example, the prompt can help AI model entities better understand the user's input intent and respond accordingly.

[0134] For example, before sending the aforementioned prompt to the AI ​​model entity, the first entity can obtain the user's intent and generate a prompt based on that intent. Optionally, the user can input the user intent to the first entity through a terminal device, or the user intent can be input to the first entity through an open interface, or the terminal can send the aforementioned user intent to the first entity, so that the first entity can generate a prompt based on the user intent and provide it to the AI ​​model entity. The AI ​​model entity can then determine the network topology based on the prompt. The AI ​​model entity provides the determined network topology to the first entity, which then sends the network topology information and task requirement information to a second entity. The second entity creates a first network instance based on the network topology information and task requirement information, enabling flexible orchestration of network functions and / or application functions based on user intent, providing customized network services to users, and improving the intelligence level of the wireless network.

[0135] Optionally, the system including the first entity and the AI ​​model entity in this embodiment (which can be simply referred to as the AI ​​system for ease of description) can be deployed together with the 5G core network. For example, the system can be interconnected with the network elements in the 5G core network as a new functional network element (e.g., the AI ​​system is deployed in the core network equipment shown in Figure 1).

[0136] Optionally, in this embodiment, the AI ​​system can replace the 5G core network, that is, the functions of the core network in the 5G system can be replaced by the AI ​​system (for example, the core network device shown in Figure 1 is the AI ​​system provided in this embodiment).

[0137] Specifically, user intent is used to indicate a user's needs. For example, a user intent could be "Please have network-assisted robots A-D work together to move device P from location X to location Y"; another example is "Please have the network provide location services for the user's terminal device"; yet another example is "Please have the network provide the best route between location A and location B for the user," and so on.

[0138] It should be understood that in this embodiment, the user intent is related to network functionality; that is, a user's intent is implemented by the wireless network system. However, this embodiment does not impose any limitations on the specific form of the user intent, as long as it reflects the user's needs.

[0139] As an example and not a limitation, the communication interface between the first entity and the AI ​​model entity, which can transmit data and / or signaling, is a third interface. For example, the first entity is an agent module, the AI ​​model entity is a large model, and the third interface can be called AN-MO. This embodiment does not limit the name of the third interface. The first entity can provide a prompt to the AI ​​model entity through the third interface.

[0140] There are many types of large-scale models currently available, and there may be more than one large-scale network model in the future. If each replacement or upgrade of a large-scale model requires adjusting the interface between the first entity and the large-scale model, the overhead would be significant and could introduce unpredictable network problems. Therefore, this third interface can be standardized. The prompt sent by the first entity to the large-scale model can be a predetermined pattern, and the large-scale model provided by the large-scale model vendor can correctly handle the input of this pattern. For example, the first entity sending a prompt to the AI ​​model entity could be a third message, which includes instructions, extended data, or requirements for generating results. The instructions indicate the aforementioned user intent; the extended data includes auxiliary information related to the user intent, and optionally, background knowledge of the tools; the requirements for generating results indicate the requirements for the AI ​​model entity to generate results, such as inference time, training accuracy, or data size.

[0141] Optionally, the third message may also include an example, which provides a standard scheme for the AI ​​model entity to refer to. The third message can be understood as template-based generation, that is, standardizing the format of the prompt sent by the first entity to the AI ​​model entity.

[0142] Optionally, in this embodiment, during the process of the first entity generating a prompt based on the user's intent, in order to improve the accuracy of the generated prompt, auxiliary information related to the user's intent can be obtained from the third entity based on the user's intent, and the prompt can be generated based on the obtained auxiliary information and the user's intent. Therefore, the method flow shown in Figure 5 further includes:

[0143] S511, the first entity sends a first message to the third entity, and correspondingly, the third entity receives the first message from the first entity.

[0144] For example, the third entity may also be referred to as a third functional entity, a third independent unit, a third logical module, etc. For instance, the third entity may be a memory module, which can implement a network data storage unit to store the environmental interaction data of each network instance. This application does not impose any limitations on the name of the third entity, as long as it can achieve the corresponding function.

[0145] Specifically, the first message is used to obtain auxiliary information related to the user's intent from a third entity. For example, the first message includes at least one of the following:

[0146] The user intent information, relevance requirement, or time requirement, wherein the relevance requirement indicates the relevance between the user intent and the auxiliary information, and optionally, the relevance requirement may be greater than a given relevance threshold. Additionally, the time requirement identifies the generation time of the auxiliary information, and the time requirement may be no later than or no earlier than a given time threshold.

[0147] S512, the third entity sends auxiliary information to the first entity, and correspondingly, the first entity receives the auxiliary information from the third entity.

[0148] Specifically, the auxiliary information includes interaction data of at least one network instance's operating environment and / or contextual information of network functions. Additionally, the auxiliary information may also include contextual information related to user intent, historical data related to the user intent, or prompt requirements of AI model entities.

[0149] As an example and not a limitation, the communication interface between the first entity and the third entity can transmit data and / or signaling through the first interface, that is, the first entity can send a first message to the third entity through the first interface, and the third entity can send auxiliary information to the first entity through the first interface.

[0150] For example, the first entity is the agent module, the third entity is the memory module, and the first interface can be called AN-Mem. This embodiment does not impose any limitations on the name of the first interface. Optionally, this embodiment does not impose any limitations on the way the third entity stores data, and the way the first entity obtains data from the third entity can be standardized. For example, the first entity can obtain which type of data from the third entity, the relevance requirements between the obtained data and the user intent, and the time requirements between the obtained data and the user intent, etc.

[0151] In this embodiment, the first entity can obtain auxiliary information related to the user's intent from the third entity based on the user's intent, and generate a prompt based on the obtained auxiliary information and the user intent. For example, if the user intent received by the first entity is "Please have network-assisted robots A to D cooperate to move device P from location X to location Y", the first entity can obtain knowledge of the robot's action pattern, historical information such as whether the AI ​​model entity has previously programmed similar tasks from the third entity, and then generate a prompt.

[0152] Furthermore, after receiving the aforementioned prompt, the AI ​​model entity in this embodiment can orchestrate network functions and / or application functions to generate a network topology in response to the prompt. Therefore, the method flow shown in Figure 5 further includes:

[0153] In S520, the AI ​​model entity determines the network topology based on the prompt.

[0154] The network topology in this embodiment includes at least one function, which is interconnected to form a topology structure. For example, the network topology includes at least one network function, which is interconnected; or, for example, the network topology includes at least one application function, which is interconnected; or, for example, the network topology includes at least one network function and at least one application function, which are interconnected.

[0155] In this context, network functions refer to the inherent functions of each network element within the network. These functions can be defined in relevant standards (e.g., 3GPP standards). For example, they could be the functions of various network elements in the 5G core network, or computing, sensing, and AI functions that may be defined in future communication networks. Application functions refer to applications, which may not be defined in relevant standards and are provided to the network by a third party. Examples include image classification, environmental modeling, or text generation. In this embodiment, the network topology generated by the AI ​​model entities can be combined with application functions and / or network functions to better realize user intent within the network.

[0156] For example, the network topology may also be referred to as application network topology, topology, or function set, etc. In this embodiment, the name of the network topology is not limited in any way, and it can include at least one network function, and at least one function can be interconnected with each other.

[0157] As one possible implementation, the AI ​​model entity determines the network topology based on the prompt, including:

[0158] The AI ​​model entity determines a thought chain based on the prompt, which includes at least one step required to achieve the user's intent. Further, the AI ​​model entity matches at least one network function and / or application function to each of the at least one step based on background knowledge. The at least one network function and / or at least one application function are interconnected to form a network topology.

[0159] As another possible implementation, the AI ​​model entity determines the network topology based on the prompt, including: the AI ​​model entity determines the network topology based on the prompt and background knowledge.

[0160] In this embodiment, the background knowledge includes descriptive information about network functions and / or descriptive information about application functions. The network function description information describes the network function, including but not limited to describing the function's purpose, effects, computational requirements, execution time requirements, or examples of the network function. The application function description information describes the application function, including but not limited to describing the function's purpose, effects, computational requirements, execution time requirements, or examples of the application function.

[0161] For example, background knowledge can be the content of a third entity (e.g., a memory module), or it can be a file in a fourth entity (e.g., a tool module).

[0162] In this embodiment, the AI ​​model entity can acquire background knowledge through the following implementation methods:

[0163] As one possible implementation, the AI ​​model entity can acquire background knowledge from a prompt provided by a first entity. For example, the first entity determines a prompt, where the extended data of the prompt includes, but is not limited to, two parts: one part is auxiliary information related to user intent, and the other part is background knowledge. The first entity can then acquire this background knowledge from a third entity.

[0164] As another possible implementation, background knowledge can be presented as a file in a fourth entity (e.g., a tool module), which the AI ​​model entity accesses to obtain the background knowledge.

[0165] In this embodiment, the network topology includes at least one network function and / or at least one application function. The network function includes at least one of the following: connectivity, computing, sensing, or AI. The application function includes at least one of the following: image classification, image statistics, environmental modeling, path planning, target recognition, or text generation.

[0166] In one possible implementation, at least one network function and / or at least one application function included in the network topology are provided by a fourth entity. This fourth entity may also be referred to as a fourth functional entity, a fourth independent unit, or a fourth logical module, etc. For example, the fourth entity could be a tools module, serving as a library of tools storing network and application functions, supporting AI model entities in generating the network topology. This application does not impose any limitations on the name of the fourth entity, as long as it can implement the corresponding functions.

[0167] To facilitate understanding, Figure 6 provides a brief overview of the network and application functions included in the fourth entity. As shown in Figure 6, the network functions included in the fourth entity include, but are not limited to: data forwarding, computation offloading, perception and control, data collection, and model training. Among these, data forwarding is a connectivity function, computation offloading is a computation function, perception is a control and perception function, and data collection and model training are AI functions.

[0168] The application functions included in the fourth entity include, but are not limited to: target recognition, path planning, environment modeling, image statistics, and text recognition.

[0169] For example, the first entity and the fourth entity can communicate via a fourth interface to transmit data and / or signaling. Optionally, the first entity is an agent module, the fourth entity is a tools module, and the fourth interface can be called AN-Tools. This embodiment does not impose any limitations on the name of the fourth interface. For instance, information related to network functions and / or application functions stored by the fourth entity can be registered in the first entity via the fourth interface. The content registered in the first entity can be standardized; for example, the fourth entity sends registration information to the first entity via the fourth interface. This registration information includes the identifier, description, input parameters, output parameters, and usage method of the function (network function or application function).

[0170] To facilitate understanding, we will use specific examples to illustrate how AI model entities generate network topology:

[0171] Example 1: The user intent is "Please have network-assisted robots A to D work together to move device P from location X to location Y".

[0172] After receiving the prompt, the AI ​​model entity can understand the user's intent and related information based on the prompt, decompose the user's intent, and output a chain of thought, as follows:

[0173] ① Obtain the robot identifier input by the user;

[0174] ② Obtain the robot's registration information (e.g., capabilities, location) based on the robot's identifier, configure the leader and follower, and perform service authentication for each robot;

[0175] ③ Query nearby base stations based on the robot's location, and configure the sensing functions (e.g., sensing policy) of the robot and nearby base stations respectively to collect environmental data, identify objects in the surrounding environment (e.g., moving objects and / or obstacles), and estimate the distance between the robot and the objects.

[0176] ④ The network and robots collaborate to plan the positioning of multiple robots (e.g., orientation, posture, position, etc.). The network performs global multi-robot orientation planning, and each robot infers its own positioning based on the global orientation.

[0177] ⑤ The network and robots collaborate to plan multi-robot grasping, with the network performing global planning (e.g., movement, position, orientation, etc.) and each robot performing local reasoning.

[0178] ⑥ The network and robots collaborate on path planning. The network performs global path planning (e.g., direction of movement, trajectory of movement, etc.), while each robot performs local path reasoning.

[0179] After determining the above thought chain, the registration information of the fourth entity can be combined to match the corresponding network functions and / or application functions for each step (i.e., ① to ⑥ in Example 1 above, a total of 6 steps) to generate the final network topology.

[0180] For example, regarding ① obtaining the robot identifier input by the user from the prompt above.

[0181] For example, in response to ② above, the network function #2 in the fourth entity (e.g., the UDM entity) can be invoked to obtain the robot's registration information.

[0182] For example, regarding ③ above, network function #3 in the fourth entity can be invoked to trigger the corresponding function through network configuration. For instance, service authentication and policy configuration can be performed on the robot, and the perception policy can be configured for the access network device and the terminal device (i.e., the robot).

[0183] It should be understood that the above example is only for the purpose of facilitating the understanding of the process of AI model entities generating network topology, and does not constitute any limitation on the scope of protection of this application.

[0184] Furthermore, after the AI ​​model entity generates the network topology, it can provide the network topology to the first entity. Therefore, the method flow shown in Figure 5 further includes:

[0185] S530, the AI ​​model entity sends the network topology to the first entity, and correspondingly, the first entity receives the network topology from the AI ​​model entity.

[0186] As described in step S510 above regarding the first entity sending a prompt to the AI ​​model entity, the first entity and the AI ​​model entity can communicate via a third interface for transmitting data and / or signaling. This third interface can be standardized, meaning the network topology sent by the AI ​​model entity to the first entity can follow a predetermined pattern. For example, the network topology sent by the AI ​​model entity to the first entity could be that the AI ​​model entity sends a fourth message to the first entity through the third interface. This fourth message includes the name of at least one function in the network topology, the connection relationship between the at least one function, the input / output data content of each function, or the input parameter configuration of each function—that is, the standardized format of the prompt sent by the AI ​​model entity to the first entity.

[0187] In this embodiment, after receiving the aforementioned network topology, the first entity can provide the network topology information and task requirement information to the second entity creating the network instance. Therefore, the method flow shown in Figure 5 further includes:

[0188] S540, the first entity sends network topology information and task requirement information to the second entity, and correspondingly, the second entity receives network topology information and task requirement information from the first entity.

[0189] For example, the second entity may also be referred to as a second functional entity, a second independent unit, a second logical module, etc. For instance, the second entity may be an actor module, which can create specific network instances based on the network topology and perform lifecycle management for each network instance. For example, the management module in the actor module is used to implement the lifecycle management of network instances. This application does not impose any limitations on the name of the second entity, as long as it can achieve the corresponding function.

[0190] For example, the first entity and the second entity can transmit data and / or signaling through a second interface. Optionally, the first entity is an agent module, the second entity is an actor module, and the second interface can be called AN-Act. This embodiment does not limit the name of the second interface. For example, the first entity can send a second message to the second entity through the second interface. The second message includes network topology information and task requirement information. The network topology information includes, but is not limited to, the identifiers of at least one function included in the network topology, and the relationships between these functions. For example, the network topology information includes the identifiers of functions such as sensing, inference, configuration, or deployment, and the relationships between these functions. The task requirement information is used to indicate the QoS requirements of the first network instance.

[0191] S550, the second entity creates the first network instance based on the network topology information and task requirement information.

[0192] Specifically, in this embodiment, after receiving network topology information and task requirement information from the first entity, the second entity can create a first network instance based on the network topology information and task requirement information. For example, the second entity determines the configuration parameters of at least one function included in the network topology according to the task requirement information, wherein the at least one function includes at least one network function and / or at least one application function.

[0193] In one possible implementation, the creation of the first network instance by the second entity includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals.

[0194] Optionally, for the situation shown in Example 1 above, the creation of the first network instance by the second entity may include the configuration of the access network device and the terminal, such as the configuration of sensing parameters (including sensing time and location), resource requirements, and corresponding policy configurations. Additionally, for the situation shown in Example 1 above, the creation of the first network instance by the second entity may also include the deployment of network functions and / or application functions.

[0195] In one possible implementation, during the operation of the first network instance, the second entity can provide the operational data of the first network instance to the third entity, which will then record and save it. For example, the management function of the second entity can provide the interaction data of the first network instance's operating environment to the third entity.

[0196] In one possible implementation, the second entity in this embodiment can also perform lifecycle management of each network instance. For example, deleting and / or updating the first network instance.

[0197] For example, the second entity deleting the first network instance includes: reclaiming the computing resources corresponding to the first network instance and deleting the identifier of the first network instance. Optionally, after the second entity deletes the first network instance, it does not need to notify the aforementioned third entity and / or the first entity; the second entity can manage the network instance itself, avoiding unnecessary signaling overhead.

[0198] For example, updating the first network instance by the second entity includes: after receiving update information from the first entity, the second entity updates the first network instance. The update information includes an identifier of the first network instance, and the update information indicates that the first network instance should be updated; or,

[0199] The second entity updates the first network instance, including: after detecting an event that triggers the update of the first network instance, the second entity updates the first network instance. The event includes at least one of the following: network function and / or application function failure, movement of the terminal device, movement of the access network device, deterioration of the transmission link quality between the terminal device and the access network device, or service congestion on the access network device.

[0200] As an example, and not a limitation, in the case where the creation of the first network instance by the second entity includes the deployment of network functions, the configuration of access network devices, and the configuration of terminals, the method flow shown in Figure 5 further includes:

[0201] S560: The terminal, access network device, or network function receives the corresponding configuration information from the second entity.

[0202] Among them, configuration information #1 received by the terminal indicates the configuration of the terminal during the creation of the first network instance; configuration information #2 received by the access network device indicates the configuration of the access network device during the creation of the first network instance; and configuration information #3 received by the network function indicates the configuration of the network function during the creation of the first network instance.

[0203] S570: Terminals, access network devices, or network functions are configured based on configuration information.

[0204] Specifically, after receiving the corresponding configuration information, the terminal, access network device, or network function can configure itself based on the configuration information and execute the corresponding tasks.

[0205] In the communication method shown in Figure 5, the process of the second entity creating a network instance based on the received network topology information and task requirement information includes the deployment of network functions, as well as the configuration of access network devices and terminals in the wireless network. The network topology is obtained by the AI ​​model entity orchestrating network functions and / or application functions based on the prompt input by the first entity, and the prompt is generated based on user intent. In other words, the system deployed on the wireless network can flexibly orchestrate network functions and / or application functions based on user intent, providing customized network services to users and improving the intelligence level of the wireless network.

[0206] As can be seen from the above, in the communication method shown in Figure 5, there are communication interfaces between the various functional entities to facilitate data and / or signaling transmission between them. For ease of understanding, the following uses the first entity as the proxy module, the AI ​​model entity as the large model, the second entity as the execution module, the third entity as the memory module, and the fourth entity as the tool library module as an example, combined with Figures 7 and 8 to introduce the system architecture of the communication method shown in Figure 5, which includes functional entities such as the first entity, the AI ​​model entity, and the second entity, as well as the form of the communication interfaces between the various functional entities.

[0207] As shown in Figure 7, the proxy module implements the network proxy function, coordinating other components (such as the large model, memory module, execution module, or tool library module) to create corresponding network instances based on user intent. The large model can be a large model applied in the communication network field, capable of orchestrating network and application functions. The tool library module can be a library of tools storing network and application functions, called by the large model to generate the network function topology. The execution module can create specific network instances based on the network function topology and perform lifecycle management for each network instance (as shown in Figure 7, this management is implemented by the execution module). The memory module can be a network data storage unit, storing the environmental interaction data of each network instance. Furthermore, as shown in Figure 7, creating a network instance includes deploying network functions, RAN configuration, and UE configuration.

[0208] For example, arrow "1" in Figure 7 can be understood as the proxy module receiving user intent, as shown in Figure 5 above. The specific description of the proxy module obtaining user intent can be found in the explanation in Figure 5, which will not be repeated here.

[0209] For example, arrow "2" in Figure 7 can be understood as the agent module sending a prompt to the large model, and the large model sending the network topology to the agent module, such as steps S510 and S530 in Figure 5 above.

[0210] For example, arrow "3" in Figure 7 can be understood as the agent module receiving information provided by the memory module. For instance, as shown in Figure 5 above, the agent module obtains auxiliary information related to intent from the memory module.

[0211] For example, arrow "4" in Figure 7 can be understood as the large model receiving information provided by the memory module. For instance, as shown in Figure 5 above, the large model obtains interactive data of the network instance runtime environment from the memory module.

[0212] For example, arrow "5" in Figure 7 can be understood as the management function (or control function) of the execution module providing interactive data of the network instance runtime environment to the memory module.

[0213] For example, the arrow "6" shown in Figure 7 can be understood as the management function of the execution module obtaining interactive data from the network instance runtime environment.

[0214] For example, the arrow "7" shown in Figure 7 can be understood as the proxy module receiving information provided by the tool library module. For instance, the large model shown in Figure 5 above obtains background knowledge from the tool library module.

[0215] For example, the arrow "8" shown in Figure 7 can be understood as the network instance calling a function in the tool library module at runtime.

[0216] For example, the arrow "9" shown in Figure 7 can be understood as the agent module providing information to the execution module, such as S540 shown in Figure 5 above.

[0217] For example, arrow "10" in Figure 7 can be understood as the execution module controlling network instances through management functions.

[0218] For example, arrow "11" shown in Figure 7 can be understood as including, but not limited to, at least one of the following in the process of creating a network instance: RAN configuration, UE configuration, or deployment of network functions.

[0219] As shown in Figure 8, the communication interfaces between the proxy module and other modules include the third interface, the fourth interface, the second interface, and the first interface. The details of each communication interface are as follows:

[0220] Interface #1: The external interface of the proxy module, which can be called AN-API. User intents can be input to the proxy module through this AN-API.

[0221] The third interface: the interface between the proxy module and the large model, which can be called AN-MO. It takes a prompt as input and outputs the network topology. Currently, there are many large models, and in the future, there may be more than one option for the network's large model. If the proxy module needs to adjust its interface and method of using the large model every time it is replaced or upgraded, it will be highly decoupled and may introduce unpredictable network problems. Therefore, this interface can be standardized. That is, the network topology of the prompt input and output sent by the proxy module to the large model can be defined in a predetermined format, and the large model vendor provides a large model that can correctly process the input of this pattern and provide the required output.

[0222] The fourth interface: the interface between the proxy module and the tool library module, which can be called AN-Tools. The tool library (including network functions and application functions) needs to register with the proxy module. The registration content can be standardized, for example, including the name, description, input parameters, output parameters, or usage method of the function.

[0223] The first interface: the interface between the proxy module and the memory module, which can be called AN-Mem. The memory module can store data in different ways, and the way the proxy module retrieves data from the memory module can be standardized. For example, the type of data to retrieve, relevance requirements, time requirements, etc.

[0224] The second interface, known as AN-Act, is the interface between the proxy module and the execution module. The proxy module can send network topology-related information to the execution module.

[0225] Other interfaces are as follows:

[0226] Interface #2: Used by the proxy module to configure the UE and base station according to the service orchestration, and can be called AN-N1 / N2.

[0227] Interface #3: This is the data plane interface between the base station and the network instance, and can be referred to as AN-N3. It is used to forward data from the base station and / or data from the UE to the application network, in which at least one network instance is deployed.

[0228] Interface #4: This is the control interface between the proxy module and the network instance, and can be referred to as AN-N4. It is used for the lifecycle management of the network instance.

[0229] It should be understood that the sequence number of each process 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.

[0230] It should also be understood that, unless otherwise specified or logically conflicting, the terminology and / or descriptions in the various embodiments of this application are consistent and can be referenced interchangeably. Furthermore, technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0231] The communication method provided in the embodiments of this application has been described in detail above with reference to Figures 5 to 8. The above communication method is mainly introduced from the perspective of interaction between various entities. It can be understood that, in order to achieve the above functions, the first entity, the AI ​​model entity, the second entity, etc., include the corresponding hardware structure and / or software module for executing each function.

[0232] Those skilled in the art will recognize that, based on the units and algorithm steps described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is implemented in hardware or by computer software driving hardware 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.

[0233] The communication device provided in this application will be described in detail below with reference to Figures 9 and 10. It should be understood that the description of the device embodiments corresponds to the description of the method embodiments. Therefore, for details not described in detail, please refer to the method embodiments above; for brevity, some details will not be repeated.

[0234] This application embodiment can divide the first entity, AI model entity, or second entity into functional modules according to the above method example. For example, each function can be divided into its own functional modules, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. The following description uses the division of functional modules according to each function as an example.

[0235] Figure 9 is a schematic block diagram of a communication device 10 provided in an embodiment of this application. The device 10 includes a transceiver unit 11 and a processing unit 12. The transceiver unit 11 can implement corresponding communication functions, and the processing unit 12 is used for data processing. In other words, the transceiver unit 11 is used to perform operations related to receiving and sending, while the processing unit 12 is used to perform other operations besides receiving and sending. The transceiver unit 11 can also be referred to as a communication interface or communication unit.

[0236] Optionally, the device 10 may further include a storage unit 13, which may be used to store instructions and / or data. The processing unit 12 may read the instructions and / or data in the storage unit so that the device can perform the operation of the device in the aforementioned method embodiments.

[0237] In one design, the device 10 may correspond to the first entity in the above method embodiments, or a component of the first entity (such as a chip).

[0238] The device 10 can implement the steps or processes corresponding to the first entity executed in the above method embodiment, wherein the transceiver unit 11 can be used to perform the transceiver-related operations of the first entity in the above method embodiment, and the processing unit 12 can be used to perform the processing-related operations of the first entity in the above method embodiment.

[0239] In one possible implementation, transceiver unit 11 is configured to send a prompt to the AI ​​model entity, the prompt being generated based on user intent. Transceiver unit 11 is also configured to receive a network topology from the AI ​​model entity, the network topology being generated based on the prompt. The network topology is used to create a first network instance, and creating the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals.

[0240] When the device 10 is used to execute the method in FIG5, the transceiver unit 11 can be used to execute the steps of transmitting and receiving information in the method, such as steps S511, S512, S510, S530 and S540; the processing unit 12 can be used to execute the processing steps in the method.

[0241] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0242] In another design, the device 10 may correspond to the AI ​​model entity in the above method embodiments, or a component of the AI ​​model entity (such as a chip).

[0243] The device 10 can implement the steps or processes corresponding to the AI ​​model entity executed in the above method embodiment. The transceiver unit 11 can be used to perform operations related to the transmission and reception of the AI ​​model entity in the above method embodiment, and the processing unit 12 can be used to perform operations related to the processing of the AI ​​model entity in the above method embodiment.

[0244] In one possible implementation, transceiver unit 11 is configured to receive a prompt from a first entity, the prompt being generated based on user intent. Processing unit 12 is configured to determine a network topology based on the prompt. Transceiver unit 11 is further configured to send the network topology to the first entity, wherein the network topology is used to create a first network instance, the creation of the first network instance including at least one of network function deployment, access network device configuration, and terminal configuration.

[0245] When the device 10 is used to execute the method in FIG5, the transceiver unit 11 can be used to execute the steps of transmitting and receiving information in the method, such as steps S510 and S530; the processing unit 12 can be used to execute the processing steps in the method, such as step S520.

[0246] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0247] In another design, the device 10 may correspond to the second entity in the above method embodiments, or a component of the second entity (such as a chip).

[0248] The device 10 can implement the steps or processes performed by the second entity corresponding to the method embodiment above. The transceiver unit 11 can be used to perform the transceiver-related operations of the second entity in the method embodiment above, and the processing unit 12 can be used to perform the processing-related operations of the second entity in the method embodiment above.

[0249] In one possible implementation, transceiver unit 11 is configured to receive network topology information and task requirement information from a first entity, wherein the network topology is determined based on a prompt, and the prompt is generated based on user intent. Processing unit 12 is configured to create a first network instance based on the network topology information and the task requirement information, wherein creating the first network instance includes at least one of network function deployment, access network device configuration, and terminal configuration, and the task requirement information is used to indicate the QoS requirements of the first network instance.

[0250] When the device 10 is used to execute the method in FIG5, the transceiver unit 11 can be used to execute the step of transmitting and receiving information in the method, such as step S540; the processing unit 12 can be used to execute the processing step in the method, such as step S550.

[0251] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0252] In another design, the device 10 may correspond to the terminal in the above method embodiments, or to a component of the terminal (such as a chip).

[0253] The device 10 can implement the steps or processes executed by the terminal corresponding to the above method embodiments. The transceiver unit 11 can be used to perform the transceiver-related operations of the terminal in the above method embodiments, and the processing unit 12 can be used to perform the processing-related operations of the terminal in the above method embodiments.

[0254] In one possible implementation, transceiver unit 11 is used to receive configuration information, which indicates the configuration of the terminal during the creation of the first network instance. Processing unit 12 is used to perform configuration based on the configuration information, wherein creating the first network instance includes at least one of network function deployment, access network device configuration, and terminal configuration, the first network instance is created based on network topology information and task requirement information, the network topology is determined based on a prompt, the prompt is generated based on user intent, and the task requirement information is used to indicate the QoS requirements of the first network instance.

[0255] When the device 10 is used to execute the method in FIG5, the transceiver unit 11 can be used to execute the step of transmitting and receiving information in the method, such as step S560; the processing unit 12 can be used to execute the processing step in the method, such as step S570.

[0256] It should be understood that the specific process of each unit performing the above-mentioned corresponding steps has been described in detail in the above method embodiments, and will not be repeated here for the sake of brevity.

[0257] It should also be understood that the device 10 here is embodied in the form of a functional unit. The term "unit" here can refer to an application-specific integrated circuit (ASIC), electronic circuitry, a processor (e.g., a shared processor, a proprietary processor, or a group processor, etc.) and memory for executing one or more software or firmware programs, integrated logic circuitry, and / or other suitable components supporting the described functions. In an alternative example, those skilled in the art will understand that device 10 may specifically be a mobility management network element in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the mobility management network element in the above method embodiments; or, device 10 may specifically be a terminal device in the above embodiments, and may be used to execute the various processes and / or steps corresponding to the terminal device in the above method embodiments. To avoid repetition, further details are omitted here.

[0258] The apparatus 10 of each of the above-described schemes has the function of implementing the corresponding steps performed by the entities (such as the first entity, the AI ​​model entity, and the second entity) in the above-described methods. This function can be implemented by hardware or by hardware executing corresponding software. The hardware or software includes one or more units corresponding to the above-described functions; for example, the transceiver unit can be replaced by a transceiver (e.g., the transmitting unit in the transceiver unit can be replaced by a transmitter, and the receiving unit in the transceiver unit can be replaced by a receiver), and other units, such as processing units, can be replaced by processors, which respectively execute the transceiver operations and related processing operations in each method embodiment.

[0259] In addition, the transceiver unit 11 can also be a transceiver circuit (for example, it may include a receiving circuit and a transmitting circuit), and the processing unit can be a processing circuit.

[0260] Figure 10 is a schematic diagram of another communication device 20 provided in an embodiment of this application. The device 20 includes a processor 21, which is used to execute computer programs or instructions stored in a memory 22, or to read data / signaling stored in the memory 22, to perform the methods in the above-described method embodiments. Optionally, there may be one or more processors 21.

[0261] Optionally, as shown in FIG10, the device 20 further includes a memory 22 for storing computer programs or instructions and / or data. The memory 22 may be integrated with the processor 21 or may be disposed separately. Optionally, there may be one or more memories 22.

[0262] Optionally, as shown in FIG10, the device 20 further includes a transceiver 23 for receiving and / or transmitting signals. For example, the processor 21 is used to control the transceiver 23 to receive and / or transmit signals.

[0263] As one option, the device 20 is used to implement the operations performed by the first entity in the various method embodiments described above.

[0264] As an alternative, the device 20 is used to implement the operations performed by the second entity in the various method embodiments described above.

[0265] As another option, the device 20 is used to implement the operations performed by the AI ​​model entity in the various method embodiments described above.

[0266] It should be understood that the processor mentioned in the embodiments of this application can be a central processing unit (CPU), or one or more combinations of other general-purpose processors, digital signal processors (DSPs), microprocessor units (MPUs), microcontroller units (MCUs), GPUs, field-programmable gate arrays (FPGAs), artificial intelligence processors (AI processors), or neural processing units (NPUs); or, the processor mentioned in the embodiments of this application can be an ASIC or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. A general-purpose processor can be a microprocessor or any conventional processor.

[0267] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be cache or random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: 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).

[0268] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0269] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0270] This application also provides a chip system (or processing system) including logic circuits and input / output interfaces.

[0271] The logic circuit can be a processing circuit in the chip system. The logic circuit can be coupled to a memory cell, calling instructions from the memory cell, enabling the chip system to implement the methods and functions of the embodiments of this application. The input / output interface can be an input / output circuit in the chip system, outputting processed information or inputting data or signaling information to be processed into the chip system for processing.

[0272] As one approach, the chip system is used to implement the operations performed by the first entity, the AI ​​model entity, or the second entity in the various method embodiments described above.

[0273] For example, the logic circuit is used to implement the processing-related operations performed by the first entity, the AI ​​model entity, or the second entity in the above method embodiments; the input / output interface is used to implement the sending and / or receiving-related operations performed by the first entity, the AI ​​model entity, or the second entity in the above method embodiments.

[0274] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a first entity, an AI model entity, or a second entity in the above-described method embodiments.

[0275] For example, when the computer program is executed by a computer, it enables the computer to implement the methods performed by the first entity, the AI ​​model entity, or the second entity in the various embodiments of the above methods.

[0276] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods performed by the first entity, the AI ​​model entity, or the second entity in the above-described method embodiments.

[0277] This application also provides a communication system, including the aforementioned first entity, AI model entity, and second entity. Optionally, the communication system may further include the aforementioned third entity, fourth entity, access network device, and terminal device.

[0278] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0279] 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.

[0280] 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.

[0281] In the several embodiments provided in this application, it should be understood that the disclosed apparatus 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 mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of apparatus or units may be electrical, mechanical, or other forms.

[0282] 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.

[0283] 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.

[0284] 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, server, or network device, 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.

[0285] 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, include: The first entity sends a prompt to the AI ​​model entity, the prompt being generated based on the user's intent; The AI ​​model entity determines the network topology based on the prompt; The AI ​​model entity sends the network topology to the first entity; The first entity sends the network topology information and task requirement information to the second entity; The second entity creates a first network instance based on the network topology information and the task requirement information. The creation of the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals. The task requirement information is used to indicate the Quality of Service (QoS) requirements of the first network instance.

2. The method according to claim 1, characterized in that, The method further includes: The first entity obtains auxiliary information related to the user's intent from the third entity based on the user's intent; The first entity generates the prompt based on the user intent and the auxiliary information. The auxiliary information includes interactive data of at least one network instance runtime environment and / or contextual information of network functions.

3. The method according to claim 2, characterized in that, The first entity obtains auxiliary information related to the user intent from the third entity based on the user intent, including: The first entity sends a first message to the third entity through a first interface. The first message is used to obtain auxiliary information related to the user intent from the third entity. The first message includes at least one of the following: The user intent information, relevance requirement, or time requirement, wherein the relevance requirement is used to indicate the relevance between the user intent and the auxiliary information, and the time requirement is used to identify the generation time of the auxiliary information; The first entity receives the auxiliary information from the third entity through the first interface.

4. The method according to any one of claims 1 to 3, characterized in that, The first entity sends the network topology information and task requirement information to the second entity, including: The first entity sends a second message to the second entity through a second interface. The second message includes information about the network topology and the task requirement information. The network topology information includes the identifier of each function in at least one of the functions included in the network topology and the association between the at least one function.

5. The method according to any one of claims 1 to 4, characterized in that, The first entity sends a prompt to the AI ​​model entity, including: The first entity sends a third message to the AI ​​model entity through a third interface. The third message includes instructions, extended data, or generation result requirements. The instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the generation result requirements indicate the requirements that the AI ​​model entity's generation result must meet.

6. The method according to any one of claims 1 to 5, characterized in that, The AI ​​model entity sends the network topology to the first entity, including: The AI ​​model entity sends a fourth message to the first entity through a third interface. The fourth message includes the name of at least one function in the network topology, the connection relationship between the at least one function, the input and output data content of each function, or the input parameter configuration of each function.

7. The method according to any one of claims 1 to 6, characterized in that, The second entity creates a first network instance based on the network topology information and the task requirement information, including: The second entity determines the configuration parameters of at least one function included in the network topology based on the task requirement information. The at least one function includes at least one network function and / or at least one application function.

8. A communication method, characterized in that, Applied to a first entity, the method includes: Send a prompt to the AI ​​model entity, the prompt being generated based on the user's intent; Receive the network topology from the AI ​​model entities, the network topology being generated based on the prompt. The network topology is used to create a first network instance, and the creation of the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals.

9. The method according to claim 8, characterized in that, The method further includes: Based on the user intent, obtain auxiliary information related to the user intent from a third entity; The prompt is generated based on the user intent and the assistance information. The auxiliary information includes interactive data of at least one network instance runtime environment and context information of network functions.

10. The method according to claim 9, characterized in that, The step of obtaining auxiliary information related to the user intent from a third entity based on the user intent includes: A first message is sent to the third entity via a first interface, the first message including at least one of the following: The user intent information, relevance requirement, or time requirement, wherein the relevance requirement is used to indicate the relevance between the user intent and the auxiliary information, and the time requirement is used to identify the generation time of the auxiliary information; The auxiliary information is received from the third entity through the first interface.

11. The method according to any one of claims 8 to 10, characterized in that, The method further includes: The network topology information and task requirement information are sent to the second entity, wherein the task requirement information is used to indicate the Quality of Service (QoS) requirements of the first network instance.

12. The method according to claim 11, characterized in that, Sending the network topology information and task requirement information to the second entity includes: A second message is sent to the second entity via a second interface. The second message includes information about the network topology and the task requirement information. The network topology information includes the identifier of each function in at least one of the functions included in the network topology, and the association between the at least one function.

13. The method according to any one of claims 8 to 12, characterized in that, Sending a prompt to the AI ​​model entity includes: A third message is sent to the AI ​​model entity through a third interface. The third message includes instructions, extended data, or generation result requirements. The instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the generation result requirements indicate the requirements that the AI ​​model entity's generated result must meet.

14. The method according to any one of claims 8 to 13, characterized in that, The receiving of the network topology from the AI ​​model entity includes: The system receives a fourth message from the AI ​​model entity through a third interface. The fourth message includes the name of at least one function in the network topology, the connection relationship between the at least one function, the input and output data content of each function, or the input parameter configuration of each function.

15. A communication method, characterized in that, The method, applied to artificial intelligence (AI) model entities, includes: Receive a prompt from a first entity, the prompt being generated based on user intent; Determine the network topology based on the prompt; Send the network topology to the first entity. The network topology is used to create a first network instance, and the creation of the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals.

16. The method according to claim 15, characterized in that, Determining the network topology based on the prompt includes: A thought chain is determined based on the prompt, the thought chain including at least one step required to achieve the user intent; Based on background knowledge, at least one network function and / or application function are matched for each of the at least one step.

17. The method according to claim 15 or 16, characterized in that, The network function includes at least one of the following: Connectivity, computing, sensing, or artificial intelligence (AI) functions; The application functionality includes at least one of the following: Image classification, image statistics, environment modeling, path planning, target recognition, or text generation.

18. The method according to any one of claims 15 to 17, characterized in that, The receiving of the prompt from the first entity includes: A third message is received from the first entity via a third interface. The third message includes instructions, extended data, or generation result requirements. The instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the generation result requirements indicate the requirements that the AI ​​model entity's generation result must meet.

19. The method according to any one of claims 15 to 18, characterized in that, Sending the network topology to the first entity includes: A fourth message is sent to the first entity through a third interface. The fourth message includes the name of at least one function in the network topology, the connection relationship between the at least one function, the input and output data content of each function, or the input parameter configuration of each function.

20. A communication method, characterized in that, Applied to a second entity, the method includes: Receive network topology information and task requirement information from a first entity, wherein the network topology is determined based on a prompt, and the prompt is generated based on user intent; A first network instance is created based on the network topology information and the task requirement information. The creation of the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of terminals. The task requirement information is used to indicate the Quality of Service (QoS) requirements of the first network instance.

21. The method according to claim 20, characterized in that, The step of creating a first network instance based on the network topology information and the task requirement information includes: Based on the task requirement information, determine the configuration parameters for at least one function included in the network topology. The at least one function includes at least one network function and / or at least one application function.

22. The method according to claim 20 or 21, characterized in that, The method further includes: Delete and / or update the first network instance.

23. The method according to claim 22, characterized in that, Deleting the first network instance includes: The computing resources corresponding to the first network instance are reclaimed, and the identifier of the first network instance is deleted.

24. The method according to claim 22 or 23, characterized in that, Updating the first network instance includes: Receive update information from the first entity, the update information including the identifier of the first network instance, the update information indicating that the first network instance should be updated; or, An event triggering an update of the first network instance is detected, the event including at least one of the following: The following events may occur: network function and / or application function failure, relocation of the terminal device, relocation of the access network device, deterioration of the transmission link quality between the terminal device and the access network device, or service congestion on the access network device.

25. The method according to any one of claims 20 to 24, characterized in that, The method further includes: Send the runtime data of the first network instance to the third entity.

26. The method according to any one of claims 20 to 25, characterized in that, The receipt of network topology information and task requirement information from the first entity includes: A second message is received from the first entity via a second interface. The second message includes information about the network topology and the task requirement information. The network topology information includes the identifier of each function in at least one of the functions included in the network topology and the association between the at least one function.

27. A communication method, characterized in that, include: Receive configuration information, which indicates the terminal's configuration during the creation of the first network instance; Configure based on the aforementioned configuration information. The creation of the first network instance includes at least one of the following: deployment of network functions, configuration of access network devices, and configuration of the terminal. The first network instance is created based on network topology information and task requirement information. The network topology is determined based on a prompt, the prompt is generated based on user intent, and the task requirement information is used to indicate the Quality of Service (QoS) requirements of the first network instance.

28. The method according to claim 27, characterized in that, The method further includes: Send the user intent to the first entity.

29. The method according to any one of claims 1 to 28, characterized in that, The creation of the first network instance also includes the deployment of application functionality.

30. The method according to any one of claims 1 to 29, characterized in that, The user intent is related to network functionality.

31. A communication device, characterized in that, include: One or more functional modules for performing the method as described in any one of claims 1 to 7, or one or more functional modules for performing the method as described in any one of claims 8 to 14, or one or more functional modules for performing the method as described in any one of claims 15 to 19, or one or more functional modules for performing the method as described in any one of claims 20 to 26, or one or more functional modules for performing the method as described in any one of claims 27 to 30.

32. A communication device, characterized in that, The device includes at least one processor coupled to a memory, the at least one processor being configured to execute a computer program in the memory to cause the device to perform the method as claimed in any one of claims 1 to 7, or to cause the device to perform the method as claimed in any one of claims 8 to 14, or to cause the device to perform the method as claimed in any one of claims 15 to 19, or to cause the device to perform the method as claimed in any one of claims 20 to 26, or to cause the device to perform the method as claimed in any one of claims 27 to 30.

33. A computer program product, characterized in that, The computer program product includes instructions for performing the method as described in any one of claims 1 to 30.

34. A computer-readable storage medium, characterized in that, include: The computer-readable storage medium stores a computer program; when the computer program is run on a computer, it causes the computer to perform the method as described in any one of claims 1 to 30.

35. A chip, characterized in that, The chip is installed in a communication device. The chip includes a processor and a communication interface. The processor reads instructions and runs them through the communication interface, causing the communication device to perform the method as described in any one of claims 1 to 30.

Images