Communication method and communication device

Abstract

The communication method comprises the following steps: a first entity generates a prompt based on a user intention, and sends the prompt to an AI model entity; therefore, the AI model entity can determine the network topology according to the received prompt, and the AI model entity sends the network topology to the first entity. The first entity sends the information of the network topology and the task demand information to the second entity, the second entity creates a first network instance according to the information of the network topology and the task demand information, and creation of the first network instance comprises at least one of deployment of a network function, configuration of an access network device and configuration of a terminal. According to the embodiment of the invention, the system which comprises the first entity, the AI model entity and the second entity and is deployed in the wireless network can flexibly arrange network functions and / or application functions based on the intention of a user, customized network services are provided for the user, and the intelligent degree of the wireless network is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication, in particular to a communication method and a communication device. BACKGROUND

[0002] In a fifth generation (5G) communication system, in order to meet different service quality requirements of different industries, users or services on the network, network slicing technology is generated. For example, enhanced mobile broadband (eMBB) type services such as network live broadcast and video backhaul have high requirements on transmission rate; for example, massive machine type communication (mMTC) type services such as smart agriculture and smart metering require network to support massive device access and frequent transmission of a large number of small messages; for example, ultra-reliable low latency communication (uRLLC) services such as vehicle networking and industrial control require millisecond-level latency and high reliability.

[0003] Network slicing is to provide multiple dedicated, virtualized and isolated logical networks on the same shared infrastructure, and each logical network serves a specific type of service or industry user. Each network slice can flexibly define its own logical topology, service level agreement (SLA) requirements, reliability and security level to meet the differentiated needs of different services or users.

[0004] However, the current 5G network slicing mainly provides differentiated connection capabilities of the network, and lacks the customization capability of service logic. The configuration and operation and maintenance of the entire slice network require supporting operation and maintenance costs, and the degree of intelligentization is insufficient. Therefore, how to improve the intelligentization degree of the network has become a problem to be solved. SUMMARY

[0005] The present application provides a communication method to improve the intelligentization degree of the network.

[0006] In a first aspect, a communication method is provided, including: a first entity sending a prompt to an artificial intelligence (AI) model entity, the prompt being generated based on a user intent; the AI model entity determining a network topology based on the prompt and sending the network topology to the first entity; and the first entity receiving the network topology, and sending information of the network topology and task requirement information to a second entity. The second entity creates a first network instance based on the information of the network topology and the task requirement information, where the creation of the first network instance includes at least one of deployment of a network function, configuration of an access network device, and configuration of a terminal, and the task requirement information is used to indicate a quality of service (QoS) requirement of the first network instance.

[0007] Based on the above technical solution, the second entity creates a network instance in a process including deployment of a network function, and configuration of an access network device and a terminal in a wireless network based on the received information of the network topology and the task requirement information. The network topology is obtained by the AI model entity based on the prompt input by the first entity, and the prompt is generated based on the user intent. That is, the system deployed in the wireless network can flexibly arrange the network function and / or application function based on the user intent, provide customized network services for the user, and improve the intelligent level of the wireless network.

[0008] In a possible design, the communication system further includes a third entity, and the method further includes: the first entity obtaining, from the third entity, auxiliary information related to the user intent based on the user intent; and the first entity generating the prompt based on the user intent and the auxiliary information, where the auxiliary information includes interaction data of at least one network instance running environment and / or context information of the network function.

[0009] Based on the above technical solution, the first entity can obtain the auxiliary information related to the user intent from the third entity based on the user intent, so that the prompt is generated by considering not only the user intent but also the obtained auxiliary information, so as to improve the accuracy of the generated prompt.

[0010] In another possible design, the first entity acquires the user-intent-related auxiliary information from the third entity according to the user intent, including: the first entity sends a first message to the third entity through a first interface, where the first message is used to acquire the user-intent-related auxiliary information from the third entity. The first message includes at least one of the following information: information of the user intent, a relevance requirement, or a time requirement, where the relevance requirement is used to indicate a relevance between the user intent and the auxiliary information, and the relevance requirement can be greater than a given relevance threshold; the time is used to identify a generation time of the auxiliary information, and the time requirement can be not later than or not earlier than a given time threshold. The first entity receives the auxiliary information from the third entity through the first interface.

[0011] Based on the technical solution described above, the first entity and the third entity can transmit data and / or signaling through the first interface. In addition, the manner in which the first entity acquires data from the third entity can be standardized. For example, which type of data the first entity can acquire from the third entity, the relevance requirement of the acquired data and the user intent, the time requirement between the acquired data and the user intent, and the like can be standardized.

[0012] In yet another possible design, the first entity sends the network topology information and the task requirement information to the second entity, including: the first entity sends a second message to the second entity through a second interface, where the second message includes the network topology information and the task requirement information, and the network topology information includes an identifier of each function of at least one function included in the network topology and an association relationship between the at least one function.

[0013] Based on the technical solution described above, the first entity and the second entity can transmit data and / or signaling through the second interface. In addition, 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 the identifier of the function and the connection relationship between the functions.

[0014] In yet another possible design, 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, where the third message includes an instruction, extension data, or a generation result requirement, where the instruction is the user intent, the extension data is the auxiliary information, and the generation result requirement is a requirement for a result generated by the AI model entity, such as inference time, training precision, data size, and the like. Optionally, the third message can further include an example, which is a standard scheme given for reference by the AI model entity.

[0015] In another possible design, the AI model entity sends the network topology to the first entity includes that the AI model entity sends a fourth message to the first entity through a third interface, and the fourth message includes a name of at least one function in the network topology, a connection relationship between the at least one function, data content of input and output of each function in the at least one function, and input parameter configuration of each function in the at least one function.

[0016] Based on the technical solution, data and / or signaling can be transmitted between the first entity and the third entity through the third interface. In addition, the manner of data transmitted by the first entity and the third entity can be standardized.

[0017] In another possible design, the second entity creates the first network instance according to the information of the network topology and the task requirement information includes that the second entity determines configuration parameters of at least one function included in the network topology according to the task requirement information, where the at least one function includes at least one network function and / or at least one application function.

[0018] In a second aspect, a communication method is provided. The method can be performed by a first entity. In the absence of special description, the "first entity" in the present application can refer to a network device (for example, an agent device or an agent module), a component (for example, a processor, a chip, or a chip system) in the network device, or a logic module or software capable of implementing all or part of the functions of the network device. For ease of description, the following description takes the first entity as an example.

[0019] The communication method includes: sending a prompt to an AI model entity, the prompt being generated based on a user intention; 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 the creation of the first network instance includes at least one of deployment of a network function, configuration of an access network device, and configuration of a terminal.

[0020] In a possible design, the method further includes: obtaining, from a third entity, auxiliary information related to the user intention according to the user intention; and generating the prompt according to the user intention and the auxiliary information, where the auxiliary information includes interaction data of at least one network instance running environment and / or context information of a network function.

[0021] In another possible design, the obtaining the user-intent-related auxiliary information from the third entity according to the user intent includes: sending a first message to the third entity through a first interface, where the first message is used to obtain the user-intent-related auxiliary information from the third entity. The first message includes at least one of the following information: information of the user intent, a relevance requirement, or a time requirement, where the relevance requirement is used to indicate a relevance between the user intent and the auxiliary information, and the relevance requirement can be greater than a given relevance threshold; the time requirement is used to identify a generation time of the auxiliary information, and the time requirement can be no later than or no earlier than a given time threshold. The auxiliary information is received from the third entity through the first interface.

[0022] In yet another possible design, the method further includes: sending information of the network topology and task requirement information to the second entity, where the task requirement information is used to indicate a quality of service (QoS) requirement of the first network instance.

[0023] In yet another possible design, the sending the information of the network topology and the task requirement information to the second entity includes: sending a second message to the second entity through a second interface, where the second message includes the information of the network topology and the task requirement information, and the information of the network topology includes an identifier of each function of at least one function included in the network topology, and an association relationship between the at least one function.

[0024] In yet another possible design, the sending the prompt to the AI model entity includes: sending a third message to the AI model entity through a third interface, where the third message includes an instruction, extension data, or a generation result requirement, the instruction indicates the user intent, the extension data includes the user-intent-related auxiliary information, and the generation result requirement indicates a requirement that a result generated by the AI model entity needs to meet, such as reasoning time, training precision, data size, and the like. Optionally, the third message can further include an example, which is a standard scheme given for the AI model entity to refer to.

[0025] In yet another possible design, the receiving the network topology from the AI model entity includes: receiving a fourth message from the AI model entity through a third interface, where the fourth message includes a name of at least one function in the network topology, a connection relationship between the at least one function, input / output data content of each function, or input parameter configuration of each function.

[0026] The technical effects of the method in the second aspect and possible designs thereof can refer to the technical effects in the first aspect and possible designs thereof.

[0027] In a third aspect, a communication method is provided. The method can be performed by an AI model entity. In the present disclosure, the AI model entity can refer to the AI model entity itself (e.g., a large model module), a component (e.g., a processor, a chip, or a chip system) in the AI model entity, or a logic module or software that can implement all or part of the functions of the AI model entity. For ease of description, the method performed by the AI model entity is described below.

[0028] 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, and the creation of the first network instance includes at least one of deployment of network functions, configuration of access network devices, and configuration of terminals.

[0029] In a possible design, the 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 respectively matching at least one network function and / or application function for the at least one step based on background knowledge.

[0030] In another possible design, the network functions include at least one of the following: connection functions, computing functions, sensing functions, or artificial intelligence (AI) functions; and the application functions include at least one of the following: picture classification, picture statistics, environment modeling, path planning, target recognition, or text generation.

[0031] In yet another possible design, the receiving the prompt from the first entity includes: receiving a third message from the first entity through a third interface, the third message including instructions, extended data, or generation result requirements, wherein the instructions indicate the user intent, the extended data includes auxiliary information related to the user intent, and the generation result requirements indicate requirements that the AI model entity needs to meet, such as inference time, training accuracy, data size, and the like. Optionally, the third message can further include an example, which is a standard scheme provided for the AI model entity to refer to.

[0032] In yet another possible design, the sending the network topology to the first entity includes: sending a fourth message to the first entity through the third interface, the fourth message including at least one of the following: a name of a function in the network topology, a connection relationship between the at least one function, input / output data content of each function, or input parameter configuration of each function.

[0033] The technical effects of the method shown in the third aspect and possible designs thereof can refer to the technical effects in the first aspect and possible designs thereof.

[0034] In a fourth aspect, a communication method is provided. The method can be performed by a second entity. In the present application, the second entity can refer to the second entity itself (for example, an actor module), a component (for example, a processor, a chip, or a chip system) in the second entity, or a logic module or software capable of realizing all or part of the functions of the second entity. For ease of description, the following description takes the second entity as an example.

[0035] The communication method includes: receiving information of a network topology and task requirement information from a first entity, the network topology being determined based on a prompt, the prompt being generated based on a user intention; and creating a first network instance according to the information of the network topology and the task requirement information, wherein the creating the first network instance includes at least one of deployment of a network function, configuration of an access network device, and configuration of a terminal, and the task requirement information is used to indicate a quality of service (QoS) requirement of the first network instance.

[0036] In a possible design, the creating the first network instance according to the information of the network topology and the task requirement information includes: determining, according to the task requirement information, a configuration parameter of at least one function included in the network topology, wherein the at least one function includes at least one network function and / or at least one application function.

[0037] In another possible design, the method further includes: deleting and / or updating the first network instance.

[0038] In yet another possible design, the deleting the first network instance includes: recycling a computing resource corresponding to the first network instance, and deleting an identifier of the first network instance.

[0039] In yet another possible design, the updating the first network instance includes: receiving update information from the first entity, the update information including an identifier of the first network instance, and the update information indicating that the first network instance is to be updated; or detecting an event triggering the updating of the first network instance, the event including at least one of the following: failure of a network function and / or an application function, movement of the terminal device, movement of the access network device, deterioration of a transmission link quality between the terminal device and the access network device, or traffic congestion of the access network device.

[0040] In yet another possible design, the method further includes: sending running data of the first network instance to a third entity.

[0041] In a further possible design of the method, the receiving the information of the network topology and the task requirement information from the first entity comprises: receiving, by the second interface, a second message from the first entity, the second message comprising the information of the network topology and the task requirement information, wherein the information of the network topology comprises an identification of each function of at least one function included in the network topology and an association relationship between the at least one function.

[0042] The technical effects of the method according to the fourth aspect and possible designs thereof can refer to those of the first aspect and possible designs thereof.

[0043] In a fifth aspect, a communication method is provided. The method can be applied to a terminal device, which can be, for example, a terminal device or a communication module in a terminal device, or a circuit or chip (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core) responsible for communication functions in a terminal device.

[0044] In the method, the terminal device receives configuration information, the configuration information indicating a configuration of the terminal in a process of creating a first network instance. The terminal device is configured based on the configuration information, wherein the creating the first network instance comprises at least one of a deployment of a network function, a configuration of an access network device, and the configuration of the terminal, the first network instance being created based on information of a network topology and task requirement information, the network topology being determined based on a prompt, the prompt being generated based on a user intent, and the task requirement information being used to indicate a QoS requirement of the first network instance.

[0045] In a possible design, the terminal device sends the above-mentioned user intent to the first entity, so that the first entity can generate a prompt based on the user intent and provide the prompt to an AI model entity, so that the AI model entity can determine the network topology according to the prompt. The AI model entity provides the determined network topology to the first entity, and the first entity sends information of the network topology and task requirement information to a second entity, and the second entity creates the first network instance according to the information of the network topology and the task requirement information, thereby realizing flexible orchestration of network functions and / or application functions based on the user intent, providing customized network services for users, and improving the intelligent degree of a wireless network.

[0046] The technical effects of the method according to the fifth aspect and possible designs thereof can refer to those of the first aspect and possible designs thereof.

[0047] In a sixth aspect, the present application provides a communication apparatus, which has the functions of the second aspect to the fifth aspect, and the communication apparatus includes modules or units or means corresponding to the operations of the second aspect to the fifth aspect, which can be implemented by software or hardware, or by a combination of software and hardware.

[0048] In a seventh aspect, the present application provides a communication apparatus, which includes at least one processor coupled with a memory. The memory is configured to store part or all of the necessary computer programs or instructions for implementing the functions of the first aspect. The at least one processor can execute the computer programs or instructions, and when the computer programs or instructions are executed, the communication apparatus implements the method in any possible design or implementation manner of the second aspect to the fifth aspect.

[0049] In a possible design, the communication apparatus can further include an interface circuit, and the processor is configured to communicate with other apparatuses or components through the interface circuit.

[0050] In a possible design, the communication apparatus can further include the memory. Optionally, the memory and the processor are integrated together.

[0051] The communication apparatus can be the terminal of the fifth aspect, or a communication module in the terminal, or a chip responsible for the communication function in the terminal, such as a Modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module.

[0052] In an eighth aspect, the present 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 in any one of the implementation manners of the first aspect to the fifth aspect.

[0053] In a ninth aspect, the present application provides a communication system, which includes a first entity for executing the method in the second aspect, an AI model entity for executing the method in the third aspect, and a second entity for executing the method in the fourth aspect.

[0054] Optionally, the communication system further includes a terminal for executing the method in the fifth aspect.

[0055] In a tenth aspect, the present application provides a computer-readable storage medium, which stores computer-readable instructions. When a computer reads and executes the computer-readable instructions, the computer executes the method in any possible design of the first aspect to the fifth aspect.

[0056] In an eleventh aspect, the present application provides a computer program product, which, when executed by a computer, causes the computer to perform the method in any possible design of the first aspect to the fifth aspect. BRIEF DESCRIPTION OF DRAWINGS

[0057] Figure 1 is a schematic diagram of a communication system suitable for the present application.

[0058] Figure 2 is a schematic diagram of an AI agent.

[0059] Figure 3 is a schematic diagram of a network slice.

[0060] Figure 4 is a schematic diagram of a network slice management architecture.

[0061] Figure 5 is a schematic flow chart of a communication method provided by the present application.

[0062] Figure 6 is a schematic diagram of a tool library provided by the present application.

[0063] Figure 7 is a schematic diagram of a communication system provided by the present application.

[0064] Figure 8 is a schematic diagram of a communication interface between various functional entities in a communication system provided by the present application.

[0065] Figure 9 is a schematic block diagram of a communication apparatus 10 provided by an embodiment of the present application.

[0066] Figure 10 is a schematic diagram of another communication apparatus 20 provided by an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to facilitate understanding of the embodiments of the present application, the following points are first explained.

[0068] First, in the present application, “for indicating” can include for directly indicating and for indirectly indicating. When describing that certain indication information is for indicating A, it can include that the indication information directly indicates A or indirectly indicates A, and does not mean that A must be carried in the indication information.

[0069] The information indicated by the indication information is referred to as to-be-indicated information. In a specific implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of specific information can also be implemented by means of the arrangement order of each information agreed in advance (for example, a protocol stipulates), thereby reducing the indication overhead to a certain extent. Meanwhile, a common part of each information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0070] Secondly, in the present application, "at least one" refers to one or more, and "more" refers to two or more (including two). In addition, in the embodiments of the present application, "first", "second", and various numerical numbers (for example, "#1", "#2", and the like) are only for the convenience of description and do not limit the scope of the embodiments of the present application. The size of the serial number of each process below does not mean the order of execution, and the execution order of each process should be determined according to its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application. It should be understood that the objects thus described can be interchanged under appropriate circumstances, so as to be able to describe schemes other than the embodiments of the present application. In addition, in the embodiments of the present application, the words such as "S510" are only for the convenience of description and do not limit the order of execution steps.

[0071] Thirdly, in the embodiments of the present application, the words such as "exemplary" or "for example" are used to represent an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. On the contrary, the words such as "exemplary" or "for example" are used to present the related concept in a specific manner.

[0072] Fourthly, in the embodiments of the present application, "saving" can refer to saving in one or more memories. The one or more memories can be separately arranged or integrated in the encoder or decoder, the processor, or the communication device. The one or more memories can be partially separately arranged and partially integrated in the processor or the communication device. The type of the memory can be any form of storage medium, and the present application does not limit this.

[0073] Fifthly, in the embodiments of the present application, the term "protocol" can refer to a standard protocol in the field of communication, for example, can include the NR protocol and the related protocol applied in the future communication system, and the present application does not limit the same.

[0074] Sixthly, in the embodiments of the present application, the terms "of", "corresponding", "relevant", "corresponding" and "associated" can be used interchangeably, and it should be pointed out that the meanings expressed are consistent when the differences are not emphasized.

[0075] Seventhly, in the embodiments of the present application, the terms "in the case of", "when", "if" can be used interchangeably, and it should be pointed out that the meanings expressed are consistent when the differences are not emphasized.

[0076] Eighthly, the term "and / or" in the present application is only used to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in the present application generally represents an "or" relationship between the associated objects.

[0077] Ninthly, the terms "message", "information" or "information element (IE)" can be used interchangeably in the present application, and the names of the message or information are not limited in any way as long as the corresponding functions can be realized.

[0078] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0079] The technical solutions of the embodiments of the present application can be applied to various communication systems, for example: a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD), a 5th generation (5G) system such as a new radio (NR), a 6th generation (6G) system and the like after the 5G evolution communication system, vehicle-to-X (V2X), wherein the V2X can include vehicle to network (V2N), vehicle to vehicle (V2V), vehicle to infrastructure (V2I), vehicle to pedestrian (V2P) and the like, long term evolution-vehicle (LTE-V), vehicle networking, machine type communication (MTC), internet of things (IoT), long term evolution-machine (LTE-M), machine to machine (M2M) and the like.

[0080] In addition, the embodiments of the present application are applicable to homogeneous network and heterogeneous network scenarios, and there is no limitation on the transmission point, which can be applicable to systems such as multi-point cooperative transmission between macro base stations and macro base stations, micro base stations and micro base stations, and macro base stations and micro base stations. The embodiments of the present application are applicable to low frequency scenarios (sub 6G Hz) and high frequency scenarios (above 6G Hz), terahertz, optical communication and the like.

[0081] Figure 1 is a schematic diagram of a communication system to which the present application is applicable. As shown in Figure 1 , the communication system 100 includes at least one network device, wherein the network device can be an access network device, for example Figure 1 , the network device 111 and the network device 112; and / or, the network device can be a core network (CN) device, for example Figure 1 , the core network device 130; the communication system 100 can also include at least one terminal device, for example Figure 1At least one of the terminal device 121, the terminal device 122, and the terminal device 123 is shown. The network device and the terminal device in the communication system can communicate with each other through a wireless link, and in turn, exchange information. It can be understood that the network device and the terminal device can also be referred to as a communication device or a communication apparatus.

[0082] The access network device can be a network-side device with wireless transceiver function. The access network device can be an apparatus in a radio access network (RAN) that provides wireless communication function for terminal devices, referred to as a RAN device. The RAN can be a 3rd generation partnership project (3GPP)-related cellular system, such as a 5G mobile communication system, or a future-oriented evolved system (such as a 6G mobile communication system). The 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, the access network device can be a base station, an evolved NodeB (eNodeB), a next generation NodeB (gNB) in a 5G mobile communication system, a base station in a subsequent evolution of 3GPP, a transmission reception point (TRP), an access node in a WiFi system, a wireless relay node, a wireless backhaul node, etc. In a communication system using different radio access technologies (RATs), the name of the device with base station function can be different. For example, it can be referred to as an eNB or eNodeB in an LTE system, and as a gNB in a 5G system or an NR system. The specific name of the base station is not limited in the present application. The access network device can include one or more co-sited or non-co-sited transmission reception points. For another example, the access network device can include at least one of the following: one or more central units (CUs), one or more distributed units (DUs), and one or more radio units (RUs). In different systems, the CU (or CU-CP and CU-UP), DU, or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an open RAN (open RAN, ORAN) system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU (open DU), the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. Any of the CU (or CU-CP, CU-UP), DU, and RU in the present application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.Exemplarily, the functions of the CU can be implemented by one entity or different entities. For example, the functions of the CU are further divided, i.e., the control plane and the user plane are separated and implemented by different entities, a control plane CU entity (i.e., a CU-CP entity) and a user plane CU entity (i.e., a CU-UP entity), which can be coupled with the DU to jointly complete the functions of the access network device. For example, the CU is responsible for processing non-real-time protocols and services, implementing radio resource control (RRC), and the functions of the packet data convergence protocol (PDCP) layer. The DU is responsible for processing physical layer protocols and real-time services, implementing the functions of the radio link control (RLC) layer, the media access control (MAC) layer, and the physical (PHY) layer. In this way, part of the functions of the radio access network device can be implemented by multiple network function entities. These network function entities can be network elements in a hardware device, or software functions running on a 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 part of the physical layer processing functions, radio frequency processing, and related functions of the active antenna. Since the information of the RRC layer will eventually become the information of the PHY layer, or be converted from the information of the PHY layer, in this architecture, high-layer signaling, such as RRC layer signaling, can also be considered as being sent by the DU, or by the DU+AAU. It can be understood that the access network device can be a device including one or more of the CU node, the DU node, and the AAU node. In addition, the CU can be divided into an access network device in the radio access network (RAN), or the CU can be divided into an access network device in the core network (CN), which is not limited in the present application. For another example, in the V2X technology, the access network device can be a road side unit (RSU). The multiple access network devices in the communication system can be the same type of base station, or different types of base stations. The base station can communicate with the terminal device, or communicate with the terminal device through a relay station. In the embodiments of the present application, the device for implementing the functions of the access network device can be the access network device itself, or a device capable of supporting the access network device to implement the functions, such as a chip system or a combination device or component that can implement the functions of the access network device, which can be installed in the access network device. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0083] A terminal device can be a device or module with corresponding communication function for accessing the above communication system. The terminal device can also be referred to as user equipment (UE), terminal, user apparatus, access terminal, subscriber unit, subscriber station, mobile station, mobile, remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal apparatus, wireless communication device, user agent or user device. A communication module, circuit or chip for performing the corresponding communication function is usually arranged in the terminal. Program instructions configured for performing the corresponding communication function are also arranged in the terminal.

[0084] For example, the terminal in the embodiments of the present application can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer (Pad), a drone, a computer with wireless transceiver function, a machine type communication (MTC) terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a smart point of sale (POS) machine, a customer-premises equipment (CPE), a light UE, a reduced capability UE (REDCAP UE), a wearable device (such as a smart watch, a smart bracelet, a pedometer, smart glasses, etc.), an internet of things (IoT) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical, a wireless terminal in smart grid, a wireless terminal in transportation safety, a wireless terminal in smart city, a wireless terminal in smart home (such as a game console, a smart TV, a smart speaker, a smart refrigerator, and fitness equipment, etc.), a transport vehicle with wireless communication function, a communication module, a roadside unit (RSU) with terminal function, a flight device (such as a smart robot, a hot air balloon, a drone, an airplane). The terminal device can also be a vehicle device, such as a whole vehicle device, a vehicle-mounted module, a vehicle-mounted chip, an on-board unit (OBU), or a telematics box (T-BOX), etc.

[0085] The main function of the core network device is to provide user connection, management of users, and completion of bearer for services, and to provide an interface to external networks as a bearer network.

[0086] Exemplarily, the core network device can include one or more of the following functional network elements:

[0087] An application function (AF) network element, an access and mobility management function (AMF) network element, a session management function (SMF) network element, a network slice selection function (NSSF) network element, a unified data management (UDM) network element, a network function repository function (NRF) network element, and the like.

[0088] Among them, the AF is configured to provide application layer information; the AMF is configured to be responsible for access control and mobility management of the terminal device 110 accessing the operator network; the SMF network element is responsible for managing the protocol data unit (PDU) session of the terminal; the NSSF network element is configured to be responsible for determining a network slice instance and selecting an AMF; the UDM is responsible for storing information of a subscribed user in the operator network; and the NRF can be used to maintain real-time information of network functions and services in the network. It should be understood that the core network device can also include other network elements, which are not described here.

[0089] In addition, without special description, the core network device in the present application can also be other devices capable of realizing corresponding functions. For example, an AI model entity, a memory module, an execution module, or a proxy module, etc. deployed with an AI model.

[0090] It can be understood that the above-mentioned network elements or functions can be either a physical entity in a hardware device, or a software instance running on a dedicated hardware, or a virtualized function instantiated on a shared platform (for example, a cloud platform), and the present application does not make any limitation on the specific form and name of the above-mentioned network elements.

[0091] It should also be understood that the above-mentioned AF, AMF, NSSF, UDM, or NRF, etc. can be understood as network elements in the core network for realizing different functions, which can be combined into a network slice as needed. These core network network elements can be independent devices respectively, or can be integrated into the same device to realize different functions, and the present application does not make any limitation on the specific form of the above-mentioned network elements.

[0092] It should also be understood that the above naming is only defined for the convenience of distinguishing different functions, and should not constitute any limitation on the present application. The present application does not exclude the possibility of using other names in 5G networks and future other networks. For example, in a 6G network, part or all of the above network elements can continue to use the terms in 5G, or other names may be used, etc.

[0093] The access network device, the terminal device and the core network device can be deployed on land, including indoor or outdoor, handheld or vehicle-mounted; can also be deployed on the water surface; can also be deployed on the aircraft, balloon and satellite in the air. The present application does not limit the scene where the network device, the terminal device and the core network device are located.

[0094] In order to facilitate the understanding of the embodiments of the present application, first, the basic concepts involved in the present application are explained.

[0095] 1. Communication and artificial intelligence (AI) integration: In the 6G vision published by the International Telecommunication Union-Radio Communication Sector (ITU-R), new service scenarios that 6G networks need to support are described, such as immersive communication, intelligent industry and digital medical treatment, etc. These new services have various differences in performance requirements, greatly increasing the complexity of network functions and the difficulty of management and configuration. In order to better provide services for these new services, 6G networks need to have strong on-demand customization capabilities to configure various functions and resources in the network in a more flexible and dynamic way. With the steady development and rapid popularization of AI technology, the introduction of AI can help achieve this goal.

[0096] Thus, the basic concept of the integration of communication and AI, namely network AI, is proposed. Network AI provides a complete AI environment and AI services through a unified architecture design within the network. Optionally, the integration of 6G communication and AI can be manifested as the integration of communication and large models.

[0097] 2. Large model technology: A large model refers to a neural network model containing a super large scale of parameters (usually more than one billion), which has the following characteristics:

[0098] 1) Huge scale: A large model contains tens of billions of parameters, and the model size can reach hundreds of gigabytes (GB) or even larger. Such a huge model size provides a large model with strong expression and learning capabilities.

[0099] 2) Multi-task learning: Large models often learn multiple different natural language processing (NLP) tasks, such as machine translation, text summarization, or question answering systems. This can enable the model to learn more general and generalized language understanding capabilities.

[0100] 3) Powerful computing resources: Training large models often requires hundreds or even thousands of graphics processing units (GPUs), as well as significant amounts of time, often weeks to months. This can accelerate the training process while preserving the capabilities of large models.

[0101] 4) Abundant data: Large models require large amounts of data for training, and large amounts of data can take advantage of the parameter size advantage of large models.

[0102] Large models are widely used in natural language processing and are changing the state of NLP tasks, leading to more powerful and intelligent language technology. Large models are an important direction of AI development. At the same time, large models also have excellent performance in various natural language processing tasks, such as text classification, sentiment analysis, summary generation, or translation. In addition, large models can be used in automatic writing, chat robots, virtual assistants, voice assistants, or automatic translation in multiple application fields.

[0103] It should be understood that the application of large models in networks requires a series of supporting functions to truly realize their potential. This system engineering can be called an AI agent (AI Agent). The AI agent is briefly described below.

[0104] 3、AI Agent: As shown in Figure 2 , in the autonomous agent system supported by large language models (LLM), LLM serves as the brain of the agent and is supplemented by several key components:

[0105] 1) Planning, including but not limited to:

[0106] Sub-goal decomposition: The agent decomposes large tasks into smaller, manageable sub-goals, enabling effective handling of complex tasks. For example, through a chain of thoughts (CoT) indicating that the model "thinks step by-step", more test time computation is utilized to break down difficult tasks into smaller, simpler steps. CoT transforms large tasks into multiple manageable tasks and elucidates the explanation of the model's thought process.

[0107] Reflection and improvement: the agent can self-criticize and reflect on past behavior, learn from mistakes, and improve future steps to improve the quality of the final result.

[0108] 2) memory, also known as storage, including but not limited to:

[0109] Short-term memory: use the short-term memory of the model to learn.

[0110] Long-term memory: provides the agent with the ability to retain and recall information for a long time (infinite), usually by using external vector storage and fast retrieval.

[0111] 3) tools, including but not limited to:

[0112] The agent obtains additional information missing in the model weights by calling external application programming interfaces (APIs), including current information, code execution capabilities, access to proprietary information sources, etc.

[0113] 4) action, the model performs a specific task and records the results.

[0114] 4、Network slicing technology: In the 5G era, in order to meet the different service quality requirements of different industries, users or businesses on the network, such as eMBB type of business such as network live broadcast, video backhaul, which requires high transmission rate, intelligent agriculture, intelligent meter reading, etc. mMTC type of business needs network to support massive device access and a large number of small message frequent, vehicle networking, industrial control, etc. uRLLC business requires millisecond level of delay and high reliability, resulting in network slicing technology.

[0115] As shown in Figure 3 , network slicing is to provide multiple dedicated, virtualized, and isolated logical networks on the same shared infrastructure, each logical network serving a specific business type or industry user (e.g. eMBB application, mMTC application, uRLLC application, 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, etc. to meet the differentiated needs of different businesses or users.

[0116] 5、Network slicing management architecture: Figure 4A three-layer network slice management architecture is shown, in which a communication service management function (CSMF) is responsible for converting relevant service requirements into slice-related requirements (such as SLA) and sending them to a slice management function (NSMF). The NSMF is responsible for the management of network slice instances and derives slice subnet instance-related requirements from slice instance-related requirements and sends the slice subnet instance requirements to a network slice subnet management function (NSSMF).

[0117] The NSSMF includes an access network NSSMF (AN-NSSMF), a transport network NSSMF (TN-NSSMF), and a core network NSSMF (CN-NSSMF). The AN-NSSM is responsible for the management of network slice subnet instances in each domain of the RAN network, the TN-NSSMF is responsible for the management of network slice subnet instances in each domain of the TN network, and the CN-NSSMF is responsible for the management of network slice subnet instances in each domain of the CN network.

[0118] When a terminal wants to access a network slice, the terminal carries requested network slice selection assistance information (requested NSSAI) in a request message sent to a base station, and the base station selects an initial AMF. The initial AMF queries the subscription NSSAI (subscribed NSSAI) of the terminal from the UDM, 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 the configured NSSAI of the initial AMF contains the NSSAI that the terminal is allowed to access. If not, the initial AMF does not support the slice and needs to perform AMF reselection. The initial AMF sends the terminal's subscribed NSSAI, requested NSSAI, and terminal location to the NSSF. The NSSF selects a target AMF that can support the slice and returns the target AMF information and NRF identifier and other information to the initial AMF. The initial AMF obtains the IP address of the target AMF from the NRF and sends the terminal's request to the target AMF, which completes the terminal's access.

[0119] 6、prompt: In an AI large model, the role of prompt is mainly to give the AI model entity a prompt for the context of input information and the parameter information of input model. When training a supervised learning or unsupervised learning model, prompt can help the model better understand the intention of the input and make a corresponding response. In addition, prompt can also improve the explainability and accessibility of the model.

[0120] In simple terms, prompt is to provide a "prompt" or "guide" to the AI model entity to help the AI model entity better understand and complete the task.

[0121] 7、AI model entity: can implement part or all AI-related operations. Illustratively, an AI model is deployed in the AI model entity. The AI model entity can also be referred to as an AI node, an AI device, an AI entity, an AI module, or an AI unit, etc. The AI model entity can be considered as a specific method to implement AI functions. The AI model entity represents the mapping relationship or function between the input and output of the model. AI functions can include one or more of the following: data collection, model training (or model learning), model information publishing, model inference (or model reasoning, reasoning, or prediction, etc.), model monitoring or model verification, or inference result publishing, etc. AI functions can also be referred to as AI (related) operations or AI-related functions.

[0122] The AI module is used to implement the corresponding AI function. The AI modules deployed in different network elements can be the same or different. The model of the AI module can implement different functions according to different parameter configurations. The model of the AI module can be configured based on one or more of the following parameters: structure parameters (such as at least one of the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of neurons, the activation function of neurons, or the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of input parameters), or output parameters (such as the type of output parameters and / or the dimension of output parameters). The bias in the activation function can also be referred to as the bias of the neural network.

[0123] An AI module can have one or more models. A model can infer an output including one parameter or multiple parameters. The learning process, training process, or inference process of different models can be deployed in different nodes or devices, or can be deployed in the same node or device.

[0124] The above is combined with Figure 1The application provides a communication method, which can be applied to the communication system as shown in FIG. 1. Figure 3 and Figure 4 The 5G network slicing technology is introduced. As known from the above, the 5G network slicing mainly provides differentiated network connection capability, and lacks the customization capability of service logic. In addition, the customization of the slicing network is very complex, and the user needs to configure the network parameters according to the needs, which has a high threshold. The configuration and operation of the entire slicing network need to be matched with the operation cost, and the intelligent degree is insufficient.

[0125] The application provides a communication method, which can be applied to the communication system as shown in FIG. 1. Figure 1 In order to apply the AI Agent idea in the wireless network, the network function and / or application function are flexibly arranged based on the user intention, the customized network service is provided for the user, and the user experience is improved.

[0126] It should be understood that the embodiments shown below do not particularly limit the specific structure of the execution subject of the method provided by the embodiments of the application, as long as the program recording the code of the method provided by the embodiments of the application can be run to communicate according to the method provided by the embodiments of the application.

[0127] For example, the execution subject of the method provided by the embodiments of the application can be an entity. In the case of no special description, the "entity" in the application can refer to the device itself (for example, an agent module, a memory module, an actor module, or an AI model entity), a component in the device (for example, a processor, a chip, or a chip system), or a logical module or software capable of realizing all or part of the device functions.

[0128] Figure 5 is a schematic flowchart of the communication method provided by the application.

[0129] S510, the first entity sends a prompt to the AI model entity, and correspondingly, the AI model entity receives the prompt from the first entity.

[0130] Exemplarily, the first entity can also be referred to as a first function entity, a first independent unit, a first logical module, or a controller, etc. For example, the first entity is an agent module, which can coordinate other components (such as a memory module, an actor module, or an AI model entity) based on the user intention to create a corresponding network instance. The name of the first entity in the application is not limited in any way, as long as the corresponding function can be realized.

[0131] In addition, the AI model entity in this embodiment is a module capable of determining a network topology based on a prompt, and can also be referred to as an AI module, an AI network element, a large model, etc. For example, the AI model entity in this embodiment can be a large model, which can be used to orchestrate network functions and / or application functions, and generate a network function topology. In this application, the name of the AI model entity is not limited in any way, as long as the corresponding function can be implemented.

[0132] Specifically, the prompt is generated based on a user intent, and the prompt includes information related to the user intent. For example, the prompt can help the AI model entity better understand the user intent input by the user and make a corresponding response.

[0133] For example, the first entity can obtain a user intent before sending the prompt to the AI model entity, and generate the prompt based on the user intent. Alternatively, the user can input the user intent to the first entity through a terminal device, or the user intent can also be input to the first entity through an open interface, or the terminal sends the user intent to the first entity, so that the first entity can generate the prompt based on the user intent and provide it to the AI model entity, so that the AI model entity can determine the network topology according to the prompt. The AI model entity provides the determined network topology to the first entity, and the first entity sends information of the network topology and task requirement information to the second entity, and the second entity creates a first network instance according to the information of the network topology and the task requirement information, realizes flexible orchestration of network functions and / or application functions based on the user intent, provides customized network services for the user, and improves the intelligent degree of the wireless network.

[0134] Alternatively, the system (for ease of description, it can be referred to as an AI system) including the first entity and the AI model entity in this embodiment can be deployed together with the 5G core network, for example, the system is connected with the network elements in the 5G core network as an additional functional network element (for example, the AI system is deployed in the core network device as shown in Figure 1 ).

[0135] Alternatively, the AI system in this embodiment 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 as shown in Figure 1 is the AI system provided in this embodiment).

[0136] Specifically, the user intent is used to indicate the user's demand. For example, the user intent can be "please network assist robots A~D to cooperate to carry device P from location X to location Y"; for another example, the user intent can be "please network provide positioning service for user's terminal device"; for another example, the user intent can be "please network provide the user with the best route between location A and location B", and the like.

[0137] It should be understood that in this embodiment, the user intent is related to the network function, that is, a certain user intent of the user is implemented by the wireless network system. However, the specific form of the user intent in this embodiment is not limited in any way, as long as it can reflect the user's demand.

[0138] By way of example but not limitation, the communication interface between the first entity and the AI model entity can transmit data and / or signaling through 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 referred to as AN-MO. The name of the third interface in this embodiment is not limited in any way. The first entity can provide a prompt to the AI model entity through the third interface.

[0139] There are many kinds of large models at present, and there can be more than one network large model in the future. If the interface between the first entity and the large model needs to be adjusted every time the large model is replaced or upgraded, the interface overhead will be very large, and unknown network problems will also be caused. Therefore, the third interface can be standardized, that is, the prompt sent by the first entity to the large model can be a predetermined pattern, and the large model provided by the large model supplier can correctly process the input of this pattern. For example, the first entity can send a prompt to the AI model entity, that is, the first entity sends a third message to the AI model, and the third message includes instructions, extended data, or generation result requirements, wherein the instructions indicate the user intent described above; the extended data includes auxiliary information related to the user intent described above, and optionally, the extended data can also include background knowledge of tools; the generation result requirement indicates the requirement for the AI model entity to generate a result, for example, the requirement can indicate the inference time, the training accuracy, or the data size requirement.

[0140] Optionally, the third message can also include an example, which is a standard scheme given for the AI model entity to refer to. The third message can be understood as being generated based on a template, that is, the format of the prompt sent by the first entity to the AI model entity is standardized.

[0141] Optionally, in this embodiment, in order to improve the accuracy of the generated prompt, the first entity can obtain the user intent related auxiliary information from the third entity according to the user intent in the process of generating the prompt, and generate the prompt according to the obtained auxiliary information and the user intent. Figure 5 The method flowchart also includes:

[0142] 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.

[0143] For example, the third entity can also be referred to as a third functional entity, a third independent unit, a third logical module, etc. For example, the third entity is a memory module, which can realize a network data storage unit and save environment interaction data of each network instance running. In this application, the name of the third entity is not limited, as long as it can realize the corresponding function.

[0144] Specifically, the first message is used to obtain the user intent related auxiliary information from the third entity. For example, the first message includes at least one of the following information:

[0145] The information of the user intent, the relevance requirement, or the time requirement, wherein the relevance requirement is used to indicate the relevance between the user intent and the auxiliary information. Optionally, the relevance requirement can be greater than a given relevance threshold. In addition, the time requirement is used to identify the generation time of the auxiliary information, and the time requirement can be no later than or no earlier than a given time threshold.

[0146] S512, the third entity sends the auxiliary information to the first entity, and correspondingly, the first entity receives the auxiliary information from the third entity.

[0147] Specifically, the auxiliary information includes at least one of the interaction data of the network instance running environment and / or the context information of the network function. In addition, the auxiliary information can also include the user intent related context information, the user intent related historical data, or the prompt requirement of the AI model entity, etc.

[0148] As an example but not limited to, the first entity and the third entity can communicate through a communication interface that transmits data and / or signaling through a first interface, that is, the first entity can send the first message to the third entity through the first interface, and the third entity can send the auxiliary information to the first entity through the first interface.

[0149] For example, the first entity is an agent module, the third entity is a memory module, and the first interface can be referred to as AN-Mem. In this embodiment, the name of the first interface is not limited. Alternatively, in this embodiment, the manner in which the third entity stores data is not limited, and the manner in which 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 degree of relevance between the obtained data and the user intent, the time requirement between the obtained data and the user intent, and the like.

[0150] In this embodiment, the first entity can obtain user intent-related auxiliary information from the third entity based on the user 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 the above-mentioned "please network assist robots A-D to cooperate to move device P from location X to location Y", the first entity can obtain knowledge of robot action patterns, historical information of whether the AI model entity has previously arranged similar tasks, and the like from the third entity, and then generate a prompt.

[0151] Further, after the AI model entity receives the prompt in this embodiment, the AI model entity can generate a network topology by arranging network functions and / or application functions in response to the prompt, and then Figure 5 The method flowchart also includes:

[0152] S520, the AI model entity determines the network topology according to the prompt.

[0153] The network topology in this embodiment includes at least one function, and the at least one function is connected to form a topology structure. For example, the network topology includes at least one network function, and the at least one network function is connected; for another example, the network topology includes at least one application function, and the at least one application function is connected; for another example, the network topology includes at least one network function and at least one application function, and the at least one network function and the at least one application function are connected.

[0154] Among them, the network function refers to the function carried by each network element in the network, which can be defined in the relevant standard (for example, 3GPP standard), for example, it can be various network element functions in the 5G core network, and it can also be computing, sensing, AI functions and the like that can be defined in subsequent 6G networks. Application function refers to application (application), which can be provided to the network by a third party without being defined in the relevant standard, such as image classification, environment modeling, or text generation, etc. The network topology generated by the AI model entity in this embodiment can be combined with the application function and / or the network function, and the user intent can be better implemented in the network.

[0155] Exemplarily, the network topology can also be referred to as an application network topology, a topology, or a function set, etc. In this embodiment, the name of the network topology is not limited, and at least one network function and mutual connection between at least one function are included.

[0156] As a possible implementation manner, the AI model entity determines the network topology according to the prompt, including:

[0157] The AI model entity determines the thought chain according to the prompt, and the thought chain includes at least one step required to achieve the user intent. Further, the AI model entity respectively matches at least one network function and / or application function for at least one step based on the background knowledge. Wherein, the at least one network function and / or at least one application function are mutually connected to form a network topology.

[0158] As another possible implementation manner, the AI model entity determines the network topology according to the prompt, including: the AI model entity determines the network topology according to the prompt and the background knowledge.

[0159] In this embodiment, the background knowledge includes description information of the network function and / or description information of the application function. Wherein, the description information of the network function is used to describe the network function, including but not limited to the function of the network function, the effect of the network function, the computing power requirement of the network function, the execution time requirement of the network function, or the example of the network function, etc.; the description information of the application function is used to describe the application function, including but not limited to the function of the application function, the effect of the application function, the computing power requirement of the application function, the execution time requirement of the application function, or the example of the application function, etc.

[0160] Exemplarily, the background knowledge can be the content of the third entity (such as a memory module), or the background knowledge can be a file in the fourth entity (such as a tool module).

[0161] In this embodiment, the AI model entity can obtain the background knowledge through the following implementation manners:

[0162] As a possible implementation manner, the AI model entity can obtain the background knowledge from the prompt provided by the first entity. For example, the first entity determines the prompt, wherein the extension data of the prompt contains but is not limited to two parts, one part is the auxiliary information related to the user intent, and the other part is the background knowledge. Wherein, the first entity can obtain the background knowledge from the third entity.

[0163] As another possible implementation, the background knowledge can be a file in a fourth entity (e.g., a tools module), and the AI model entity obtains the background knowledge by accessing the file.

[0164] In this embodiment, the network topology includes at least one network function and / or at least one application function, wherein the network function includes at least one of the following: a connection function, a computing function, a perception function, or an AI function. The application function includes at least one of the following: picture classification, picture statistics, environment modeling, path planning, target recognition, or text generation.

[0165] In a possible implementation, the at least one network function and / or the at least one application function included in the network topology is provided by a fourth entity. The fourth entity can also be referred to as a fourth function entity, a fourth independent unit, or a fourth logical module, etc. For example, the fourth entity is a tools module, which is a tool library for saving network functions and application functions, and supports the AI model entity to call and generate a network topology. In this application, the name of the fourth entity is not limited in any way, as long as the corresponding function can be implemented.

[0166] For ease of understanding, the following describes the AI model entity generating a network topology in combination with specific examples: Figure 6 The network functions and application functions included in the fourth entity are briefly introduced. From the perspective of Figure 6 As can be seen from Table 1, the network functions included in the fourth entity include but are not limited to: data forwarding, computing offloading, perception control, data collection, and model training, etc. Among them, data forwarding belongs to the connection function, computing offloading belongs to the computing function, perception belongs to the control perception function, and data collection and model training belong to the AI function.

[0167] The application functions included in the fourth entity include but are not limited to: target recognition, path planning, environment modeling, picture statistics, and text recognition, etc.

[0168] Exemplarily, the first entity and the fourth entity can transmit data and / or signaling through a communication interface of a fourth interface. Optionally, the first entity is an agent module, and the fourth entity is a tools module. The fourth interface can be referred to as AN-Tools. In this embodiment, the name of the fourth interface is not limited in any way. For example, the fourth entity saves the related information of the network functions and / or application functions, and can register the information in the first entity through 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 through the fourth interface, and the registration information includes the identification, description, input parameter, output parameter, and usage of the function (network function or application function).

[0169] For ease of understanding, the following describes the AI model entity generating a network topology in combination with specific examples:

[0170] Example 1: The user's intention is "Please network assist robots A~D to cooperate to carry device P from location X to location Y".

[0171] After the AI model entity receives the prompt, it can learn the user's intention and information related to the user's intention based on the prompt, decompose the user's intention, and output the chain of thought as follows:

[0172] ① Obtain the robot identifier input by the user;

[0173] ② Obtain the registration information of the robot (such as capability, location, etc.) according to the robot identifier, configure the leader and follower, and perform service authentication for each robot;

[0174] ③ Query the nearby base station according to the robot location, and configure the sensing function (such as sensing policy) of the robot and the nearby base station to collect environmental data, identify the items (such as carrying items and / or obstacles, etc.) in the surrounding environment, and estimate the distance between the robot and the items;

[0175] ④ Network and robot cooperation for multi-robot station (such as direction, posture, position, etc.) planning, network for global multi-robot position planning, each robot based on global position for reasoning of its own station;

[0176] ⑤ Network and robot cooperation for multi-robot grasping planning, network for global planning (such as movement, position, direction, etc.), each robot for local reasoning;

[0177] ⑥ Network and robot cooperation for path planning, network for global path planning (such as movement direction, movement trajectory, etc.), each robot for local path reasoning.

[0178] After determining the chain of thought described above, the corresponding network function and / or application function can be matched for each step (i.e. ① to ⑥ in the above example 1, a total of 6 steps) combined with the registration information of the fourth entity, to generate the final network topology.

[0179] For example, for the above ① from the prompt to obtain the robot identifier input by the user.

[0180] For example, for the above ②, the network function #2 (such as UDM entity) in the fourth entity can be called to obtain the registration information of the robot.

[0181] For example, for the above-mentioned ③, a network function #3 in the fourth entity can be invoked to trigger the corresponding function through network configuration. For example, service authentication and policy configuration are performed on the robot, and a perception policy is configured to the access network device and the terminal device (i.e., the robot).

[0182] It should be understood that the above example one is only for the convenience of understanding the process of generating a network topology by an AI model entity, and does not constitute any limitation on the protection scope of the present application.

[0183] Further, after the AI model entity generates the network topology, the network topology can be provided to the first entity, and then Figure 5 The method flowchart also includes:

[0184] 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.

[0185] As can be seen from the description of the step S510 about the first entity sending the prompt to the AI model entity, the communication interface between the first entity and the AI model entity can transmit data and / or signaling through a third interface, and the third interface can be standardized, that is, the AI model entity sending the network topology to the first entity can be a predetermined mode. For example, the AI model entity sending the network topology to the first entity can be that the AI model entity sends a fourth message to the first entity through the third interface, and 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, that is, the format of the prompt sent by the AI model entity to the first entity is standardized.

[0186] In this embodiment, after the first entity receives the above-mentioned network topology, the first entity can provide the information of the network topology and the task requirement information to the second entity for creating a network instance, and then Figure 5 The method flowchart also includes:

[0187] S540, the first entity sends the information of the network topology and the task requirement information to the second entity, and correspondingly, the second entity receives the information of the network topology and the task requirement information from the first entity.

[0188] Exemplarily, the second entity can also be referred to as a second function entity, a second independent unit, a second logical module, etc. For example, the second entity is an actor module, which can create specific network instances based on the network topology and perform lifecycle management of each network instance. Exemplarily, a management module in the actor module is used to implement the lifecycle management of the network instance. The name of the second entity in the present application is not limited in any way, as long as it can implement the corresponding function.

[0189] Exemplarily, the first entity and the second entity can transmit data and / or signaling through the second interface. Optionally, the first entity is an agent module, and the second entity is an actor module. The second interface can be referred to as AN-Act. The name of the second interface in this embodiment is not limited in any way. For example, the first entity can send a second message to the second entity through the second interface, and the second message includes network topology information and task requirement information. The network topology information includes but is not limited to the identification of at least one function included in the network topology and the association relationship between the at least one function. For example, the network topology information includes the identification of a perception function, an inference function, a configuration function, or a deployment function, and the association relationship between the functions. The task requirement information is used to indicate the QoS requirement of the first network instance.

[0190] S550, the second entity creates the first network instance according to the network topology information and the task requirement information.

[0191] Specifically, in this embodiment, after the second entity receives the network topology information and the task requirement information from the first entity, the second entity can create the first network instance based on the network topology information and the 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, where the at least one function includes at least one network function and / or at least one application function.

[0192] In a possible implementation, the second entity creating the first network instance includes at least one of the following: deployment of a network function, configuration of an access network device, and configuration of a terminal.

[0193] Optionally, for the case shown in Example One, the second entity creating the first network instance can include configuration of an access network device and configuration of a terminal, such as configuration of a perception parameter (including time and direction of perception), configuration of a resource requirement, and corresponding policy configuration. In addition, for the case shown in Example One, the second entity creating the first network instance can also include deployment of a network function and / or deployment of an application function.

[0194] In a possible implementation, during the running of the first network instance, the second entity can provide running data of the first network instance to a third entity for recording and saving by the third entity. For example, a management function of the second entity can provide interaction data of a running environment of the first network instance to the third entity.

[0195] In a possible implementation, the second entity in this embodiment can also perform lifecycle management of each network instance. For example, the second entity can delete and / or update the first network instance.

[0196] Exemplarily, the second entity deletes the first network instance, including: recycling the computing resource 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, the third entity and / or the first entity described above can not need to be notified, and the management of the network instance can be implemented by the second entity itself, avoiding unnecessary signaling overhead.

[0197] Exemplarily, the second entity updates the first network instance, including: after the second entity receives the update information from the first entity, the second entity updates the first network instance. The update information includes the identifier of the first network instance, and the update information indicates updating the first network instance; or,

[0198] The second entity updates the first network instance, including: after the second entity detects an event triggering 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, transmission link quality deterioration between the terminal device and the access network device, or service congestion of the access network device.

[0199] As an example but not limitation, in the case that the second entity creates the first network instance including deployment of the network function, configuration of the access network device, and configuration of the terminal, Figure 5 The method flowchart also includes:

[0200] S560, the terminal, the access network device, or the network function receives the corresponding configuration information from the second entity.

[0201] Among them, the configuration information #1 received by the terminal indicates the configuration of the terminal in the process of creating the first network instance; the configuration information #2 received by the access network device indicates the configuration of the access network device in the process of creating the first network instance; and the configuration information #3 received by the network function indicates the configuration of the network function in the process of creating the first network instance.

[0202] S570, the terminal, the access network device, or the network function configures based on the configuration information.

[0203] Specifically, after the terminal, the access network device, or the network function receives the corresponding configuration information, it can configure based on the configuration information and perform corresponding tasks.

[0204] Figure 5In the illustrated communication method, the process of creating a network instance by the second entity based on the received information of the network topology and the information of the task requirement includes the deployment of network functions, and the configuration of access network devices in the wireless network and the configuration of terminals. The network topology is obtained by the AI model entity based on the prompt input by the first entity to arrange the network functions and / or application functions, and the prompt is generated based on the user intention. That is, the system for wireless network deployment can flexibly arrange the network functions and / or application functions based on the user intention, provide customized network services for users, and improve the intelligent level of the wireless network.

[0205] From the above, Figure 5 In the illustrated communication method, there is a communication interface between each functional entity to facilitate data and / or signaling transmission between each functional entity. For ease of understanding, the following takes the first entity as the agent 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, and introduces the communication interface between each functional entity in combination with Figure 7 and Figure 8 introduced Figure 5 In the illustrated communication method, the system architecture including the first entity, the AI model entity, and the second entity, and the form of the communication interface between each functional entity.

[0206] From Figure 7 , it can be seen that the agent module implements the proxy function of the network, coordinates other components (such as the large model, the memory module, the execution module, or the tool library module, etc.) based on the user intention to create a corresponding network instance. The large model can be a large model applied in the field of communication network, which can arrange network functions and application functions. The tool library module can be a tool library that saves network functions and application functions, which is called by the large model to generate a network function topology. The execution module can create a specific network instance based on the network function topology, and perform the life cycle management of each network instance (such as the management in Figure 7 is implemented by the execution module). The memory module can be a network data storage unit that saves the environment interaction data of each network instance running. In addition, from Figure 7 , it can be seen that creating a network instance includes deploying network functions, RAN configuration, and UE configuration.

[0207] For example, Figure 7 , the arrow “1” can be understood as the agent module receiving the user intention, as shown in the above Figure 5 , the agent module obtains the user intention, and the description of the agent module specifically obtaining the user intention can refer to the description in Figure 5 , which will not be described here.

[0208] For another example, Figure 7The arrow "2" shown in the middle can be understood as the agent module sending a prompt to the large model, and the large model sending network topology to the agent module, as described above Figure 5 Steps S510 and S530 shown in the middle.

[0209] For another example, Figure 7 The arrow "3" shown in the middle can be understood as the agent module receiving information provided by the memory module, as described above Figure 5 The agent module shown in the middle obtains the intent-related auxiliary information from the memory module.

[0210] For another example, Figure 7 The arrow "4" shown in the middle can be understood as the large model receiving information provided by the memory module, as described above Figure 7 The large model shown in the middle obtains the interaction data of the network instance running environment from the memory module.

[0211] For another example, Figure 7 The arrow "5" shown in the middle can be understood as the management function (or control function) of the execution module providing the interaction data of the network instance running environment to the memory module.

[0212] For another example, Figure 5 The arrow "6" shown in the middle can be understood as the management function of the execution module obtaining the interaction data of the network instance running environment.

[0213] For another example, Figure 7 The arrow "7" shown in the middle can be understood as the agent module receiving information provided by the tool library module, as described above Figure 7 The large model shown in the middle obtains background knowledge from the tool library module.

[0214] For another example, Figure 5 The arrow "8" shown in the middle can be understood as the network instance runtime calling the function in the tool library module.

[0215] For another example, Figure 7 The arrow "9" shown in the middle can be understood as the agent module providing information to the execution module, as described above Figure 7 S540 shown in the middle.

[0216] For another example, Figure 8 The arrow "10" shown in the middle can be understood as the execution module implementing control over the network instance through the management function.

[0217] For another example, Figure 5 to Figure 8 The arrow "11" shown in the middle can be understood as including but not limited to at least one of RAN configuration, UE configuration, or deploying network functions in the process of creating a network instance.

[0218] From Figure 9As can be seen, the communication interfaces between the agent module and each module include a third interface, a fourth interface, a second interface, and a first interface, each of which is described as follows:

[0219] Interface #1: the external interface of the agent module, which can be referred to as AN-API. User intent can be input to the agent module through the AN-API.

[0220] Third interface: the interface between the agent module and the large model, which can be referred to as AN-MO. The prompt input is performed and the network topology is output. There are many large models at present, and in the future, there can be more than one option for network large models. If the interface and method of using the large model of the agent module need to be adjusted every time the large model is replaced or upgraded, it is not decoupled and can cause unknown network problems. Therefore, the interface can be standardized. That is, the prompt input sent by the agent module to the large model and the output network topology can be in a predetermined format, and the large model provider can provide a large model that can correctly process the input in this mode and give the output as required.

[0221] Fourth interface: the interface between the agent module and the tool library module, which can be referred to as AN-Tools. The tool library (including network functions and application functions) needs to be registered with the agent module, and the registration content can be standardized, for example, including the name, description, input parameters, output parameters, or usage of the function.

[0222] First interface: the interface between the agent module and the memory module, which can be referred to as AN-Mem. The memory module can store data in different ways, and the way the agent module obtains data from the memory module can be standardized. For example, which type of data to obtain, the relevance requirement, the time requirement, etc.

[0223] Second interface: the interface between the agent module and the execution module, which can be referred to as AN-Act. The agent module can send network topology-related information to the execution module.

[0224] There are other interfaces as follows:

[0225] Interface #2: used for the agent module to configure the UE and the base station according to service orchestration, which can be referred to as AN-N1 / N2.

[0226] Interface #3: the data plane interface between the base station and the network instance, which can be referred to as AN-N3. It is used to forward the data of the base station and / or the data of the UE to an application network in which at least one network instance is deployed.

[0227] Interface #4: the control interface between the agent module and the network instance, which can be referred to as AN-N4. It is used for lifecycle management of the network instance.

[0228] It should be understood that the size of the sequence number of the above processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0229] It should also be understood that in various embodiments of the present application, the terms and / or descriptions of different embodiments are consistent and can be referred to each other if there is no special description and logical conflict. In addition, the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0230] The above, combined with Figure 10 The communication method provided by the embodiments of the present application is described in detail. The above communication method is mainly introduced from the perspective of interaction between each entity. It can be understood that the first entity, the AI model entity, the second entity and the like contain the corresponding hardware structure and / or software module for executing each function in order to realize the above functions.

[0231] Those skilled in the art should realize that, in combination with the units and algorithm steps of the examples described in the embodiments disclosed herein, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is realized in hardware or computer software driven hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0232] The following will be described in detail Figure 9 and Figure 5 The communication device provided by the present application is described in detail. It should be understood that the description of the device embodiment corresponds to the description of the method embodiment. Therefore, the content not described in detail can be referred to the above method embodiment, and part of the content will not be described again for the sake of brevity.

[0233] The embodiments of the present application can divide the functional modules of the first entity, the AI model entity or the second entity according to the above method examples, for example, each functional module can be divided according to each function, or two or more functions can be integrated in one processing module. The above integrated module can be realized in the form of hardware or software functional module. It should be noted that the division of modules in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division way. The following will be described taking the division of each functional module corresponding to each function as an example.

[0234] Figure 5is a schematic block diagram of a communication apparatus 10 provided by an embodiment of the present application. The apparatus 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 configured to perform data processing. In other words, the transceiver unit 11 is configured to perform receiving and sending related operations, and the processing unit 12 is configured to perform operations other than receiving and sending. The transceiver unit 11 can also be referred to as a communication interface or a communication unit.

[0235] Optionally, the apparatus 10 can further include a storage unit 13, which can be configured to store instructions and / or data. The processing unit 12 can read the instructions and / or data in the storage unit, so that the apparatus implements the actions of the device in the foregoing various method embodiments.

[0236] In one design, the apparatus 10 can correspond to the first entity in the above method embodiments, or be a component part (such as a chip) of the first entity.

[0237] The apparatus 10 can implement the steps or processes performed by the first entity in the above method embodiments. In this case, the transceiver unit 11 can be configured to perform the transceiving related operations of the first entity in the above method embodiments, and the processing unit 12 can be configured to perform the processing related operations of the first entity in the above method embodiments.

[0238] In one possible implementation, the transceiver unit 11 is configured to send a prompt to an AI model entity, the prompt being generated based on a user intent. The transceiver unit 11 is further 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 the creation of the first network instance includes at least one of deployment of network functions, configuration of access network devices, and configuration of terminals.

[0239] When the apparatus 10 is configured to perform the method in Figure 5 , the transceiver unit 11 can be configured to perform the steps of transceiving information in the method, such as steps S511, S512, S510, S530 and S540, and the processing unit 12 can be configured to perform the processing steps in the method.

[0240] It should be understood that the specific processes by which the units perform the corresponding steps described above have been described in detail in the above method embodiments, and thus will not be described here again for brevity.

[0241] In another design, the apparatus 10 can correspond to the AI model entity in the above method embodiments, or be a component part (such as a chip) of the AI model entity.

[0242] The apparatus 10 can implement the steps or procedures performed by the second entity in the above method embodiments, wherein the transceiver 11 can be configured to perform the transceiving-related operations of the second entity in the above method embodiments, and the processor 12 can be configured to perform the processing-related operations of the second entity in the above method embodiments.

[0243] In a possible implementation, the transceiver 11 is configured to receive a prompt from a first entity, the prompt being generated based on a user intent. The processor 12 is configured to determine a network topology based on the prompt. The transceiver 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, and the creating the first network instance comprises at least one of deployment of network functions, configuration of access network devices, and configuration of terminals.

[0244] When the apparatus 10 is configured to perform the method in Figure 5 , the transceiver 11 can be configured to perform the steps of transceiving information in the method, such as steps S510 and S530, and the processor 12 can be configured to perform the processing steps in the method, such as step S520.

[0245] It should be understood that the specific process by which each unit performs the corresponding steps described above has been described in detail in the above method embodiments, and thus will not be described here for brevity.

[0246] In yet another design, the apparatus 10 can correspond to, or be a component (e.g., a chip) of, the second entity in the above method embodiments.

[0247] The apparatus 10 can implement the steps or procedures performed by the second entity in the above method embodiments, wherein the transceiver 11 can be configured to perform the transceiving-related operations of the second entity in the above method embodiments, and the processor 12 can be configured to perform the processing-related operations of the second entity in the above method embodiments.

[0248] In a possible implementation, the transceiver 11 is configured to receive information of a network topology and task requirement information from a first entity, the network topology being determined based on a prompt, the prompt being generated based on a user intent. The processor 12 is configured to create a first network instance based on the information of the network topology and the task requirement information, wherein the creating the first network instance comprises at least one of deployment of network functions, configuration of access network devices, and configuration of terminals, and the task requirement information is used to indicate a QoS requirement of the first network instance.

[0249] When the apparatus 10 is configured to perform the method in Figure 10When performing the method in the embodiment of the present invention, the transceiver unit 11 may be used to execute the steps of sending and receiving information in the method, such as step S540; the processing unit 12 may be used to execute the processing steps in the method, such as step S550.

[0250] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0251] In yet another design, the apparatus 10 may correspond to the terminal in the above method embodiment, or be a component of the terminal (such as a chip).

[0252] The device 10 can implement the steps or processes executed by the terminal in the above method embodiment, wherein the transceiver unit 11 can be used to perform the transceiver-related operations of the terminal in the above method embodiment, and the processing unit 12 can be used to perform the processing-related operations of the terminal in the above method embodiment.

[0253] In one possible implementation, a transceiver unit 11 is configured to receive configuration information indicating terminal configuration during creation of a first network instance. A processing unit 12 is configured to perform configuration based on the configuration information, wherein creation of 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 indicates QoS requirements for the first network instance.

[0254] Wherein, when the device 10 is used to perform Figure 10 When performing the method in the embodiment of the present invention, the transceiver unit 11 may be used to execute the steps of sending and receiving information in the method, such as step S560; the processing unit 12 may be used to execute the processing steps in the method, such as step S570.

[0255] It should be understood that the specific process of each unit executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0256] It should also be understood that the device 10 here is embodied in the form of a functional unit. The term "unit" here may refer to an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a dedicated processor or a group processor, etc.) and memory for executing one or more software or firmware programs, a combined logic circuit and / or other suitable components that support the described functions. In an optional example, those skilled in the art will understand that the device 10 may be specifically the mobile management network element in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the mobile management network element in the above-mentioned method embodiments; or, the device 10 may be specifically the terminal device in the above-mentioned embodiment, and may be used to execute the various processes and / or steps corresponding to the terminal device in the above-mentioned method embodiments. To avoid repetition, it will not be described here.

[0257] The device 10 of each of the above 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 method. This function can be implemented by hardware, or it can be implemented by hardware executing the corresponding software. The hardware or software includes one or more units corresponding to the above functions; for example, the transceiver unit can be replaced by a transceiver (for example, the sending 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 the processing unit, can be replaced by a processor to respectively perform the sending and receiving operations and related processing operations in each method embodiment.

[0258] In addition, the transceiver unit 11 may also be a transceiver circuit (for example, may include a receiving circuit and a sending circuit), and the processing unit may be a processing circuit.

[0259] Figure 10 FIG2 is a schematic diagram of another communication device 20 provided in an embodiment of the present application. The device 20 includes a processor 21, which is configured to execute computer programs or instructions stored in a memory 22, or read data / signaling stored in the memory 22, to perform the methods described in the above method embodiments. Optionally, there are one or more processors 21.

[0260] Alternatively, as ​ As shown, the device 20 further includes a memory 22, which is used to store computer programs or instructions and / or data. The memory 22 can be integrated with the processor 21, or can be separately provided. Optionally, there are one or more memories 22.

[0261] Alternatively, as ​As shown, the apparatus 20 further includes a transceiver 23 for signal receiving and / or sending. For example, the processor 21 is configured to control the transceiver 23 to perform signal receiving and / or sending.

[0262] As an option, the apparatus 20 is configured to implement operations performed by a first entity in the various method embodiments above.

[0263] As another option, the apparatus 20 is configured to implement operations performed by a second entity in the various method embodiments above.

[0264] As yet another option, the apparatus 20 is configured to implement operations performed by an AI model entity in the various method embodiments above.

[0265] It should be understood that the processor mentioned in the embodiments of the present application can be one or a combination of a central processing unit (CPU), a digital signal processor (DSP), a microprocessor unit (MPU), a microcontroller unit (MCU), a GPU, a field programmable gate array (FPGA), an artificial intelligence processor (AI processor), or a neural processing unit (NPU); or the processor mentioned in the embodiments of the present application can be an ASIC or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0266] It should also be understood that the memory mentioned in the embodiments of the present application can be a volatile memory and / or a non-volatile memory. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a cache, a random access memory (RAM). For example, the RAM can be used as an external cache. As an example but not limitation, the RAM includes the following various forms: static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DRRAM).

[0267] It should be noted that when the processor is a general processor, a DSP, an ASIC, a FPGA or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component, the memory (storage module) can be integrated in the processor.

[0268] It should also be noted that the memory described herein is intended to include, but not limited to, these and any other suitable types of memory.

[0269] The embodiments of the present application also provide a chip system, which can also be referred to as a processing system, including a logic circuit and an input / output interface.

[0270] Among them, the logic circuit can be a processing circuit in the chip system. The logic circuit can be coupled to the storage unit to call the instructions in the storage unit, so that the chip system can realize the methods and functions of the embodiments of the present application. The input / output interface can be an input / output circuit in the chip system, which outputs the processed information of the chip system or inputs the data or signaling information to be processed into the chip system for processing.

[0271] As a solution, the chip system is configured to implement operations performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments.

[0272] For example, the logic circuit is configured to implement operations related to processing performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments; and the input / output interface is configured to implement operations related to sending and / or receiving performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments.

[0273] The embodiments of the present application also provide a computer readable storage medium, which stores computer instructions for implementing the method performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments.

[0274] For example, the computer program, when executed by a computer, enables the computer to implement the method performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments.

[0275] The embodiments of the present application also provide a computer program product, which contains instructions, and the instructions, when executed by a computer, implement the method performed by the first entity, the AI model entity, or the second entity in each of the above method embodiments.

[0276] The embodiments of the present application also provide a communication system, which includes the first entity, the AI model entity, and the second entity described above. Optionally, the communication system further includes the third entity, the fourth entity, the access network device, and the terminal device described above.

[0277] The explanations and beneficial effects of the related contents in any of the above provided devices can refer to the corresponding method embodiments provided above, and will not be repeated here.

[0278] Those skilled in the art can clearly understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software mode depends on the specific application and design constraints of the technical solutions. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0279] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above described system, device and unit can refer to the corresponding processes in the above method embodiments, and will not be repeated here.

[0280] In several embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented by other manners. For example, the apparatus embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some interfaces, apparatuses or units, and can be electrical, mechanical or other forms.

[0281] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0282] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0283] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part of the prior art or the part of the technical solutions of the present application can be embodied in the form of software product, and the computer software product is stored in a storage medium, including a plurality of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The foregoing storage medium includes: U disk, mobile hard disk, ROM, RAM, magnetic disk or optical disk and various program code storage media.

[0284] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: Comprising: a first entity sends a prompt to an AI model entity, the prompt being generated based on a user intent; the AI model entity determines a network topology according to the prompt; the AI model entity sends the network topology to the first entity; the first entity sends information of the network topology and task requirement information to a second entity; the second entity creates a first network instance according to the information of the network topology and the task requirement information, wherein the creating a first network instance includes at least one of deployment of network functions, configuration of access network devices, and configuration of terminals, and the task requirement information is used to indicate quality of service (QoS) requirements of the first network instance.

2. The method of claim 1, wherein, The method further comprises: the first entity obtains auxiliary information related to the user intent from a third entity according to the user intent; the first entity generates the prompt according to the user intent and the auxiliary information, wherein the auxiliary information includes interaction data of at least one network instance running environment and / or context 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 a third entity according to the user intent, comprising: the first entity sends a first message to the third entity through a first interface, the first message being used to obtain the auxiliary information related to the user intent from the third entity, the first message including at least one of the following information: information of the user intent, a relevance requirement, or a 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 information of the network topology and the task requirement information to the second entity, comprising: the first entity sends a second message to the second entity through a second interface, the second message including the information of the network topology and the task requirement information, wherein the information of the network topology includes the identification of each function of at least one function included in the network topology and the association relationship 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, comprising: the first entity sends a third message to the AI model entity through a third interface, the third message including an instruction, extension data, or a generation result requirement, wherein the instruction indicates the user intent, the extension data includes auxiliary information related to the user intent, and the generation result requirement indicates the requirements that the AI model entity needs to 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, comprising: the AI model entity sends 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 the at least one function, the input / 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 according to information of the network topology and the task requirement information, including: The second entity determines 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.

8. A communication method characterized by comprising: The method applied to the first entity, the method includes: sending a prompt to an artificial intelligence AI model entity, the prompt is generated based on a user intention; receiving a network topology from the AI model entity, the network topology is generated based on the prompt, Wherein, 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 deployment of network functions, the configuration of access network devices and the configuration of terminals.

9. The method of claim 8, wherein, The method further includes: obtaining auxiliary information related to the user intention from a third entity according to the user intention; generating the prompt according to the user intention and the auxiliary information, Wherein, the auxiliary information includes interaction data of at least one network instance running environment and context information of network functions.

10. The method of claim 9, wherein, The method of obtaining auxiliary information related to the user intention from a third entity according to the user intention, including: sending a first message to the third entity through a first interface, the first message includes at least one of the following information: information of the user intention, relevance requirement, or time requirement, wherein the relevance requirement is used to indicate the relevance between the user intention and the auxiliary information, and the time requirement is used to identify the generation time of the auxiliary information; receiving the auxiliary information 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: sending information of the network topology and task requirement information to the second entity, the task requirement information is used to indicate the quality of service QoS requirement of the first network instance.

12. The method of claim 11, wherein, The method of sending information of the network topology and task requirement information to the second entity, including: sending a second message to the second entity through a second interface, the second message includes information of the network topology and the task requirement information, Wherein, the information of the network topology includes the identification of each function in at least one function included in the network topology, and the association relationship between the at least one function.

13. The method according to any one of claims 8 to 12, characterized in that The method of sending a prompt to an AI model entity, including: sending a third message to the AI model entity through a third interface, the third message includes instructions, extension data, or generation result requirements, wherein the instructions indicate the user intention, the extension data includes auxiliary information related to the user intention, and the generation result requirements indicate the requirements that the AI model entity meets.

14. The method according to any one of claims 8 to 13, characterized in that, The method of receiving a network topology from the AI model entity, including: receiving 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 method of communication, comprising: Applied to an artificial intelligence, AI, model entity, the method comprises: receiving a prompt from a first entity, the prompt being generated based on a user intent; determining a network topology according to the prompt; sending the network topology to the first entity, wherein the network topology is used to create a first network instance, the creating of the first network instance comprising at least one of deployment of network functions, configuration of access network devices, and configuration of terminals.

16. The method of claim 15, wherein, The determining of the network topology according to the prompt comprises: determining a thought chain according to the prompt, the thought chain comprising at least one step required to achieve the user intent; respectively matching at least one network function and / or application function for the at least one step based on background knowledge.

17. The method according to claim 15 or 16, characterized in that, The network function comprises at least one of: a connection function, a computing function, a perception function, or an artificial intelligence, AI, function; The application function comprises at least one of: picture classification, picture statistics, environment modeling, path planning, target recognition, or text generation.

18. The method of any one of claims 15-17, wherein, The receiving of the prompt from the first entity comprises: receiving a third message from the first entity through a third interface, the third message comprising instructions, extended data, or generation result requirements, wherein the instructions indicate the user intent, the extended data comprises auxiliary information related to the user intent, and the generation result requirements indicate requirements to be met by a result generated by the AI model entity.

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

20. A method of communication, comprising: Applied to a second entity, the method comprises: receiving information of a network topology and task requirement information from a first entity, the network topology being determined based on a prompt, the prompt being generated based on a user intent; creating a first network instance according to the information of the network topology and the task requirement information, wherein the creating of the first network instance comprises at least one of deployment of network functions, configuration of access network devices, and configuration of terminals, and the task requirement information is used to indicate quality of service, QoS, requirement of the first network instance.

21. The method of claim 20, wherein, The creating of the first network instance according to the information of the network topology and the task requirement information comprises: determining configuration parameters of at least one function comprised in the network topology according to the task requirement information, wherein the at least one function comprises at least one network function and / or at least one application function.

22. The method of claim 20 or 21, wherein, The method further comprises: deleting and / or updating the first network instance.

23. The method of claim 22, wherein, The deleting of the first network instance comprises: reclaiming a computing resource corresponding to the first network instance, and deleting an identifier of the first network instance.

24. The method of claim 22 or 23, wherein, The updating of the first network instance comprises: receiving update information from the first entity, the update information including an identity of the first network instance, the update information indicating to update the first network instance; or detecting an event triggering to update the first network instance, the event including at least one of: a network function and / or an application function failure, a movement of the terminal device, a movement of the access network device, a transmission link quality between the terminal device and the access network device becoming worse, or a traffic congestion of the access network device.

25. The method of any one of claims 20-24, wherein, The method further includes: sending running data of the first network instance to a third entity.

26. The method of any one of claims 20-25, wherein, The receiving information of a network topology and task requirement information from a first entity includes: receiving a second message from the first entity through a second interface, the second message including the information of the network topology and the task requirement information, wherein the information of the network topology includes an identity of each function of at least one function included in the network topology and an association relationship between the at least one function.

27. A method of communication, comprising: including: receiving configuration information, the configuration information indicating a configuration of a terminal in a process of creating a first network instance; configuring based on the configuration information, wherein the creating the first network instance includes at least one of a deployment of a network function, a configuration of an access network device, and the configuration of the terminal, the first network instance is created based on information of a network topology and task requirement information, the network topology is determined based on a prompt, the prompt is generated based on a user intention, and the task requirement information is used to indicate a quality of service (QoS) requirement of the first network instance.

28. The method of claim 27, wherein, The method further includes: sending the user intention to the first entity.

29. The method of any one of claims 1 to 28, wherein, The creating the first network instance further includes a deployment of an application function.

30. The method of any one of claims 1 to 29, wherein, The user intention is related to a network function.

31. A communications device, characterized by including one or more functional modules for performing the method of any one of claims 1-7, or one or more functional modules for performing the method of any one of claims 8-14, or one or more functional modules for performing the method of any one of claims 15-19, or one or more functional modules for performing the method of any one of claims 20-26, or one or more functional modules for performing the method of any one of claims 27-30. including at least one processor coupled to a memory, the at least one processor configured to execute a computer program in the memory to cause the apparatus to perform the method of any one of claims 1-7, or to cause the apparatus to perform the method of any one of claims 8-14, or to cause the apparatus to perform the method of any one of claims 15-19, or to cause the apparatus to perform the method of any one of claims 20-26, or to cause the apparatus to perform the method of any one of claims 27-30.

32. A communications device, characterized by The computer program product includes instructions for performing the method of any one of claims 1-30.

33. A computer program product, characterised in that, including:

34. A computer-readable storage medium, comprising: ​ The computer readable storage medium stores a computer program; the computer program, when running on a computer, causes the computer to execute the method in any one of claims 1 to 30.

35. A chip, characterized by The chip is installed in a communication device, the chip comprises a processor and a communication interface, the processor reads instructions through the communication interface and runs, so that the communication device executes the method in any one of claims 1 to 30.

Images