6g network intelligent layer construction and data processing method based on hierarchical ai agent and related equipment

Abstract

The application discloses a 6G network intelligent layer construction and data processing method based on hierarchical AI agents and related equipment, which can be applied to the technical field of wireless communication networks. The application sets at least one primary agent and at least one secondary agent in the 6G network intelligent layer, and the primary agent interacts with the network management system in the 6G network, the secondary agent interacts with the primary agent, and the secondary agent is deployed in the local network element. When the number of primary agents is one, the connection relationship between the primary agent and the secondary agent is constructed; when the number of primary agents is at least two, the connection relationship between the secondary agent and one of the primary agents is constructed, and other primary agents corresponding to the secondary agent are dynamically discovered through the connected primary agent; the network element is controlled and adjusted through the secondary agent and the primary agent, so that the combination application of the 6G network and the AI intelligence can be realized.

Description

Technical Field

[0001] This application relates to the field of wireless communication network technology, and in particular to a method and related equipment for constructing and processing a 6G network intelligent layer based on hierarchical AI agents. Background Technology

[0002] In related technologies, TU-R explicitly lists "AI and communication" as one of the six core application scenarios of 6G within the IMT-2030 framework, and defines "ubiquitous intelligence" as one of the four design principles. This means that AI is no longer simply layered on top of the network as in the 5G era, but is deeply integrated into every layer from the initial network architecture design. 3GPP has officially launched a 6G network architecture research project in the SA2 working group, with "AI and intelligent agents" formally included. 6G networks will support AI intelligent agents as an intrinsic capability, including AI, computing power, data, and sensing capabilities that evolve beyond traditional connectivity based on the connectivity architecture. However, existing technologies lack specific standards and specifications for building an AI intelligence layer, thus hindering the combined application of 6G networks and AI intelligence.

[0003] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0004] The main objective of this application is to propose a method and related equipment for constructing and processing a 6G network intelligent layer based on hierarchical AI agents, which can effectively realize the combined application of 6G network and AI intelligence.

[0005] To achieve the above objectives, one aspect of this application proposes a method for constructing and processing data in a 6G network intelligent layer based on hierarchical AI agents. The 6G network intelligent layer includes at least one primary intelligent agent and at least one secondary intelligent agent. The primary intelligent agent interacts with the network management system in the 6G network, and the secondary intelligent agent interacts with the primary intelligent agent. The secondary intelligent agent is deployed within a local network element. The method includes the following steps: When there is only one first-level agent, a connection relationship is established between the first-level agent and the second-level agent. When there are at least two first-level agents, a connection relationship is established between the second-level agent and one of the first-level agents. Other first-level agents in the network to which the second-level agent belongs are dynamically discovered through the connected first-level agents. The secondary intelligent agent queries the service data and system status data of the local network element, generates an analysis report of the local network element based on the service data and system status data, and then sends the service data, system status data and analysis report to the primary intelligent agent. The first-level intelligent agent determines that a local network element is abnormal based on the analysis report, the business data, or the system status data, and adjusts the configuration information of the local network element.

[0006] In some embodiments, when the number of first-level agents is one, establishing the connection relationship between the first-level agent and the second-level agent includes: In the secondary intelligent agent, the address information, symmetrically encrypted key, and certificate of the primary intelligent agent are statically configured; and in the primary intelligent agent, the address information, symmetrically encrypted key, and certificate of the secondary intelligent agent are statically configured. In the secondary intelligent agent, a request access message is generated based on the address information of the primary intelligent agent, the symmetric encrypted key, and the certificate, and the request access message is sent to the primary intelligent agent; the request access message also carries the device identifier, the network identifier, the intelligent agent identifier, the local network element type, and the local network element standard information of the secondary intelligent agent; In the first-level intelligent agent, the address information of the second-level intelligent agent, the symmetric encrypted key and certificate are verified and compared with the access request information based on the statically configured address information of the second-level intelligent agent; Once the verification is confirmed to be successful in the first-level intelligent agent, the second-level intelligent agent is connected to the first-level intelligent agent.

[0007] In some embodiments, after the secondary agent connects to the primary agent, the method further includes the following steps: The secondary agent sends a heartbeat packet to the primary agent for a first preset duration, and receives a response packet corresponding to the heartbeat packet returned by the primary agent.

[0008] In some embodiments, dynamically discovering other first-level agents in the network to which the second-level agent belongs through the connected first-level agents includes: The target first-level intelligent agent is securely connected to the first-level intelligent agent on the first-level intelligent agent discovery device. The target first-level intelligent agent includes a first-level intelligent agent connected to a second-level intelligent agent. The target first-level intelligent agent sends a dynamic discovery request to the first-level intelligent agent discovery device, and the dynamic discovery request carries the target first-level intelligent agent's own network information. The primary agent discovery device searches for a backup primary agent corresponding to its own network information based on the dynamic discovery request. Establish the connection relationship between the target first-level intelligent agent and the backup first-level intelligent agent.

[0009] In some embodiments, after the primary agent discovery device connects with the target primary agent, the method further includes the following steps: The first-level intelligent agent discovery device sends a heartbeat packet to the target first-level intelligent agent for a second preset time period, and receives a response packet corresponding to the heartbeat packet returned by the target first-level intelligent agent.

[0010] In some embodiments, querying the service data and system status data of a local network element, and generating an analysis report of the local network element based on the service data and system status data, includes: Query the business data and system status data of local network elements for the third preset time period; Based on the business data and the system status data, it is determined that the local network element is in an abnormal state, and an analysis report of the local network element is generated. The analysis report includes the anomaly point, the suspected anomaly point, and the data on which the anomaly analysis is based. Alternatively, based on the business data and the system status data, it can be determined that the local network element is not in an abnormal state, and an analysis report of the local network element can be generated, which includes identification information indicating that the local network element is in a normal state.

[0011] In some embodiments, the step of querying the service data and system status data of the local network element through the secondary intelligent agent, and generating an analysis report of the local network element based on the service data and the system status data, includes: When a primary agent connected to the secondary agent receives a network analysis command, it sends a request for a network element analysis report to the secondary agent through the primary agent. The secondary intelligent agent queries the service data and system status data of the local network element according to the request network element analysis report instruction, and determines that the local network element has an abnormal state based on the service data and system status data, generating an analysis report of the local network element including anomaly points, suspected anomalies, and data on the basis for anomaly analysis; or, it determines that the local network element does not have an abnormal state based on the service data and system status data, generating an analysis report of the local network element including identification information indicating that the local network element is in a normal state.

[0012] In some embodiments, determining that a local network element is abnormal based on the analysis report, the service data, or the system status data, and adjusting the configuration information of the local network element, includes: If an anomaly is determined in the corresponding local network element based on the analysis report, or if an anomaly is determined in the local network element based on all the service data or the system status data, a configuration modification operation message is sent to the secondary intelligent agent. In the secondary intelligent agent, the configuration modification operation of the local network element is performed according to the modified configuration operation information.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a method and related equipment for constructing and processing a 6G network intelligent layer based on hierarchical AI intelligent agents. This scheme sets up at least one primary intelligent agent and at least one secondary intelligent agent in the 6G network intelligent layer, with the primary intelligent agent interacting with the network management system in the 6G network, and the secondary intelligent agent interacting with the primary intelligent agent. Simultaneously, after deploying the secondary intelligent agent within the local network element, when there is only one primary intelligent agent, a connection relationship is established between the primary intelligent agent and the secondary intelligent agent; when there are at least two primary intelligent agents, a connection relationship is established between the secondary intelligent agent and one of the primary intelligent agents. Other primary intelligent agents belonging to the network to which the secondary intelligent agent belongs are dynamically discovered through the connected primary intelligent agents. Then, the secondary intelligent agent queries the service data and system status data of the local network element, generates an analysis report of the local network element based on the service data and system status data, and sends the service data, system status data, and analysis report to the primary intelligent agent. Finally, the primary intelligent agent determines whether there is an anomaly in the local network element based on the analysis report, service data, or system status data and adjusts the configuration information of the local network element, thereby effectively realizing the combined application of 6G network and AI intelligence. Attached Figure Description

[0017] Figure 1 This is a schematic diagram of the 6G network intelligent layer module provided in the embodiments of this application; Figure 2 This is a flowchart of the 6G network intelligent layer construction and data processing method based on hierarchical AI agents provided in the embodiments of this application; Figure 3 This is a schematic diagram illustrating the connection between a primary intelligent agent and multiple secondary intelligent agents provided in an embodiment of this application; Figure 4 This is a schematic diagram illustrating the dynamic discovery of multiple first-level intelligent agents provided in an embodiment of this application; Figure 5This is a schematic diagram illustrating the querying of local data and status by a secondary intelligent agent according to an embodiment of this application; Figure 6 This is a schematic diagram illustrating a first-level intelligent agent requesting data from a second-level intelligent agent, as provided in an embodiment of this application. Figure 7 This is a schematic diagram illustrating the control of a first-level intelligent agent calling a network element interface, provided in an embodiment of this application. Figure 8 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Before providing a detailed description of the embodiments of this application, some of the nouns and terms used in the embodiments of this application will be explained first. The nouns and terms used in the embodiments of this application shall be interpreted as follows: 5GC: 5G Core Network, is the core of the 5G mobile network. It establishes reliable and secure network connections for end users and provides access to their services. The core domain handles various essential functions in the mobile network, such as connectivity and mobility management, authentication and authorization, user data management, and policy management. 5G core network functions are entirely software-based and designed to be cloud-native, meaning they are independent of the underlying cloud infrastructure, enabling greater deployment agility and flexibility.

[0023] 6G, short for sixth-generation wireless technology, is envisioned as an intelligent, ubiquitous wireless communication network. The ultimate goal of 6G is to connect people, devices, and the environment, serving as a platform for "ubiquitous intelligent computing." Compared to 5G, 6G will represent a leap from "Internet of Everything" to "Intelligent Internet of Everything."

[0024] The functions of AMF (Access and Mobility Management Function) include connectivity management, reachability management, mobility management, and access authorization.

[0025] The functions of a UPF (User plane Function) include session points for interconnecting external PDUs with the data network, packet routing, and forwarding, such as supporting uplink classifiers to route traffic flows to the data network.

[0026] An Access Network (AN) is an implementation system in a telecommunications network that connects user terminal equipment and service nodes (such as switches and routers). It is responsible for connecting users to the core network and is the "last mile" of the communication network. Based on the transmission medium, ANs can be divided into fiber optic access, copper wire access, hybrid fiber-coaxial (HFC) access, and wireless access (WLL).

[0027] A Network Function (NF) is a functional module in a communication network responsible for performing specific tasks, such as routing management, authentication, and data transmission. In the 5G core network, the NF is a basic building block of the Service-Based Architecture (SBA).

[0028] An intelligent agent is an intelligent entity in the field of artificial intelligence that can autonomously perceive its environment, make decisions, and execute actions to achieve specific goals. Intelligent agents possess characteristics such as autonomy, responsiveness, sociality, and initiative, and can be a software program, a robot, or a system.

[0029] In related technologies, TU-R explicitly lists "AI and communication" as one of the six core application scenarios of 6G within the IMT-2030 framework, and defines "ubiquitous intelligence" as one of the four design principles. This means that AI is no longer simply layered on top of the network as in the 5G era, but is deeply integrated into every layer from the initial network architecture design. 3GPP has officially launched a 6G network architecture research project in the SA2 working group, with "AI and intelligent agents" formally included. 6G networks will support AI intelligent agents as an intrinsic capability, including AI, computing power, data, and sensing capabilities that evolve beyond traditional connectivity based on the connectivity architecture. However, existing technologies lack specific standards and specifications for building an AI intelligence layer, thus hindering the combined application of 6G networks and AI intelligence.

[0030] In view of this, this application provides a method and related equipment for constructing and processing a 6G network intelligent layer based on hierarchical AI agents, which can effectively realize the combined application of 6G network and AI intelligence.

[0031] The embodiments of this application will now be described in detail with reference to the accompanying drawings: Reference Figure 1 This application provides a schematic diagram of the modules of the 6G network intelligent layer. From... Figure 1 As can be seen, the 6G network intelligent layer in this embodiment includes at least one primary intelligent agent and at least one secondary intelligent agent. The primary intelligent agent interacts with the network management system in the 6G network, and the secondary intelligent agent interacts with the primary intelligent agent. The secondary intelligent agent is deployed within a local network element. The local network element in this embodiment includes, but is not limited to, AN, AMF, UPF, or NF. The primary intelligent agent in this embodiment can be merged with the network management system or deployed as an independent device in the 6G network architecture; the secondary intelligent agent in this embodiment can be deployed within a local network element.

[0032] Specifically, in this embodiment, the first-level intelligent agent has the authority to read historical alarms, performance data, or historical operations of other network elements collected by the network management system; it also has the authority to query specific network element service and configuration data, current status analysis, or issue upcoming configuration modifications to local network elements for analysis and obtain analysis results from the second-level intelligent agent; at the same time, when authorized by the network management system, the first-level intelligent agent has the authority to comprehensively analyze the overall network situation and call each network element interface to modify and control the network element configuration.

[0033] The Level 2 intelligent agent has read-only permissions to read the service data, configuration data, and system status of local network elements, as well as local data analysis permissions. However, it does not have the authority to modify data, modify configurations, or perform signaling scheduling. This avoids the impact of individual biased analysis and unauthorized modifications on the overall network. Furthermore, it is an independent program module in each network element and does not interact with other local network elements. Therefore, 4G and 5G network elements only need to upgrade and install the Level 2 intelligent agent module. If the Level 2 intelligent agent needs to modify data or perform any scheduling, it needs to report to the Level 1 intelligent agent, which will then call the management interface provided by the network element to perform the specific operation.

[0034] based on Figure 1 The diagram shown is as follows: Figure 2 As shown, the 6G network intelligent layer construction and data processing method based on hierarchical AI agents provided in this application embodiment may include, but is not limited to, steps S210 to S240: Step S210: When there is only one first-level agent, establish the connection relationship between the first-level agent and the second-level agent; Step S220: When there are at least two first-level agents, establish a connection relationship between the second-level agent and one of the first-level agents, and dynamically discover other first-level agents in the network to which the second-level agent belongs through the connected first-level agents. Step S230: Query the service data and system status data of the local network element through the secondary intelligent agent, generate the analysis report of the local network element based on the service data and system status data, and then send the service data, system status data and analysis report to the primary intelligent agent. Step S240: The first-level intelligent agent determines that there is an anomaly in the local network element based on the analysis report, business data or system status data, and adjusts the configuration information of the local network element.

[0035] It is understandable that, such as Figure 3 As shown, when only one primary agent is connected to multiple secondary agents, the connection can be established by statically configuring the secondary agents to directly connect to the primary agents. Specifically, the connection process in this embodiment includes the following steps: Static configuration of the address information, symmetric encryption (SSL) key, and certificate of the first-level agent in the second-level agent; and static configuration of the address information, symmetric encryption key, and certificate of the second-level agent in the first-level agent; In the secondary agent, a request access message is generated based on the address information of the primary agent, the symmetric encrypted key, and the certificate. The request access message is sent to the primary agent using the HTTP or HTTP2 protocol format. The request access message also carries the device identifier, network identifier, agent identifier, local network element type, and local network element standard information of the secondary agent. At the same time, it also provides the primary agent with a password encrypted using an asymmetric algorithm (such as RSA) or a symmetric encryption algorithm (such as AES) for the primary agent to verify access. In the first-level intelligent agent, the address information of the statically configured second-level intelligent agent, the symmetric encrypted key and certificate are verified and compared with the access request information. After the verification is confirmed to be successful, the second-level intelligent agent is connected to the first-level intelligent agent.

[0036] Specifically, in this embodiment, after the secondary intelligent agent connects to the primary intelligent agent, the secondary intelligent agent sends a heartbeat packet to the primary intelligent agent for a first preset time interval and receives a response packet corresponding to the heartbeat packet returned by the primary intelligent agent. The first preset time interval can be set according to the actual network conditions. If the primary intelligent agent does not receive a heartbeat packet from the secondary intelligent agent after the first preset time interval, the connection between the secondary intelligent agent and the primary intelligent agent is disconnected. Subsequently, if the secondary intelligent agent needs to reconnect to the primary intelligent agent, it needs to be re-authenticated to improve connection security.

[0037] It is understood that this embodiment can be based on disaster recovery deployment or multiple logical networks, setting up multiple first-level intelligent agents or deploying one first-level intelligent agent in each logical network. When multiple first-level intelligent agents exist, the connection relationship between a second-level intelligent agent and one of the first-level intelligent agents is first established. The connection relationship between a first-level intelligent agent and a second-level intelligent agent in this embodiment is the same as the connection method between only one first-level intelligent agent and a second-level intelligent agent. After the connection authentication between the second-level intelligent agent and one of the first-level intelligent agents is completed, other first-level intelligent agents in the corresponding network of the second-level intelligent agent are dynamically discovered through the connected first-level intelligent agents. Specifically, this embodiment can perform secure connection verification on the first-level intelligent agent discovery device for target first-level intelligent agents, including those connected to second-level intelligent agents; then, the target first-level intelligent agent sends a dynamic discovery request carrying its own network information to the first-level intelligent agent discovery device; the first-level intelligent agent discovery device searches for a backup first-level intelligent agent corresponding to its own network information based on the dynamic discovery request, and then establishes a connection relationship between the target first-level intelligent agent and the backup first-level intelligent agent.

[0038] like Figure 4As shown, taking Level 1 agent 01 as an example, in this embodiment, Level 2 agent first sends an access request and security authentication to Level 1 agent 01. After Level 1 agent 01 performs security verification, a connection is established. Then, Level 1 agent 01 sends registration information to the Level 1 agent discovery device to access the device. Next, Level 1 agent 01 provides its home network information to the Level 1 agent discovery device and sends a dynamic discovery request to request the discovery of a backup Level 1 agent in the corresponding home network. Then, a connection is established between the target Level 1 agent and the backup Level 1 agent. This allows the backup Level 1 agent to take over the work of the target Level 1 agent when it malfunctions or fails, effectively improving the data processing stability of the intelligent layer.

[0039] It is understood that in this embodiment, after the primary agent discovery device connects with the target primary agent, the primary agent discovery device sends a heartbeat packet to the target primary agent for a second preset time interval and receives a response packet corresponding to the heartbeat packet returned by the target primary agent. The second preset time interval in this embodiment can be set according to the actual network conditions. If the primary agent discovery device does not receive a response packet from the target primary agent after the second preset time interval, it determines that the target primary agent is unavailable and therefore deletes the registration information of the target primary agent. Simultaneously, this embodiment can synchronously call a backup primary agent to take over the work of the target primary agent, thereby effectively improving the stability of data processing.

[0040] It is understood that, after the connection between the primary and secondary intelligent agents is completed in this embodiment, the secondary intelligent agent can query the service data and system status data of the local network element, generate an analysis report of the local network element based on the service data and system status data, and then send the service data, system status data, and analysis report to the primary intelligent agent. In some embodiments, such as Figure 5 As shown, when a secondary intelligent agent is deployed to a business network element, it queries the local network element's business data and system status data after a third preset time interval. Based on the business data and system status data, it determines that the local network element is in an abnormal state and generates an analysis report for the local network element, including anomaly points, suspected anomalies, and data on the basis for anomaly analysis. Alternatively, based on the business data and system status data, it determines that the local network element is not in an abnormal state and generates an analysis report for the local network element, including identification information indicating that the local network element is in a normal state. The third preset time interval in this embodiment can be set according to actual business needs. The data on the basis for anomaly analysis in this embodiment includes, but is not limited to, data on anomaly criteria, anomaly data, anomaly users, and anomaly times.

[0041] In other embodiments, such as Figure 6As shown, when a primary agent connected to a secondary agent receives a network analysis command sent by the network administrator through the network management system, it sends a request for a network element analysis report to the secondary agent. Then, the secondary agent queries the service data and system status data of the local network element according to the request, and determines whether the local network element is in an abnormal state based on the service data and system status data, generating an analysis report for the local network element including anomalies, suspected anomalies, and data supporting the anomaly analysis. Alternatively, it determines that the local network element is not in an abnormal state based on the service data and system status data, generating an analysis report for the local network element including identification information indicating that the local network element is in a normal state. In this embodiment, the primary agent can also perform further analysis based on the original collected data sent by the secondary agent to further determine the system status of the local network element to which the secondary agent is located.

[0042] It is understood that, in this embodiment, the primary intelligent agent can adjust the configuration information of the local network element when it determines that an anomaly exists in the local network element based on analysis reports, business data, or system status data. Specifically, for example... Figure 7 As shown, this embodiment can determine the presence of anomalies in a corresponding local network element based on an analysis report, or determine the local network element with anomalies based on all service data or system status data, and send configuration modification operation information to the secondary intelligent agent; the secondary intelligent agent then performs configuration modification operations on the local network element according to the configuration modification operation information. Furthermore, this embodiment can also generate network element scheduling or control instructions after determining the network configuration to be modified according to the administrator's requirements, and then control the local network element based on the network element scheduling or control instructions. In this embodiment, the primary intelligent agent can also send configuration modification and service scheduling control information to the corresponding service network element through the network management system to realize the configuration modification process or service scheduling process of the local network element.

[0043] As described above, the secondary intelligent agent set up in this embodiment only has read-only and data analysis permissions, and can be deployed only on existing network devices. This effectively reduces the impact on existing networks and network elements. Furthermore, by deploying a lightweight secondary intelligent agent on existing network elements, the function of upgrading and accessing the 6G intelligent layer can be achieved. Simultaneously, this embodiment sets the primary intelligent agent to have the permission to obtain data from the secondary intelligent agent or the network management system, and can make decisions based on the analysis of the entire network data to call the secondary intelligent agent interface to modify device configurations and perform scheduling in the network. This achieves network security and controllability, thereby realizing the combined application of 6G networks and AI intelligence.

[0044] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0045] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0046] Please see Figure 8 , Figure 8 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 810 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 820 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 820 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 820 and is called and executed by the processor 810 using the methods described in the embodiments of this application. The input / output interface 830 is used to implement information input and output; The communication interface 840 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 850 transmits information between various components of the device (e.g., processor 810, memory 820, input / output interface 830, and communication interface 840); The processor 810, memory 820, input / output interface 830 and communication interface 840 are connected to each other within the device via bus 850.

[0047] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0048] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0049] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0050] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0051] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0052] This application provides a method and related equipment for constructing and processing a 6G network intelligent layer based on hierarchical AI agents. This method involves setting at least one primary intelligent agent and at least one secondary intelligent agent in the 6G network intelligent layer. The primary intelligent agent interacts with the network management system in the 6G network, and the secondary intelligent agent interacts with the primary intelligent agent. The secondary intelligent agent is deployed within a local network element. When there is only one primary intelligent agent, a connection is established between the primary and secondary intelligent agents. When there are at least two primary intelligent agents, a connection is established between the secondary intelligent agent and one of the primary intelligent agents. The connected primary intelligent agents dynamically discover other primary intelligent agents belonging to the network to which the secondary intelligent agent belongs. Then, the secondary intelligent agent queries the service data and system status data of the local network element, generates an analysis report based on the service data and system status data, and sends the service data, system status data, and analysis report to the primary intelligent agent. Finally, the primary intelligent agent determines whether there is an anomaly in the local network element based on the analysis report, service data, or system status data and adjusts the configuration information of the local network element accordingly. This effectively realizes the combined application of 6G network and AI intelligence.

[0053] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0054] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0055] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0056] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0057] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0058] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0059] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0060] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for constructing and processing data of a 6G network intelligent layer based on hierarchical AI agents, characterized in that, The 6G network intelligent layer includes at least one primary intelligent agent and at least one secondary intelligent agent. The primary intelligent agent interacts with the network management system in the 6G network, and the secondary intelligent agent interacts with the primary intelligent agent. The secondary intelligent agent is deployed within a local network element. The method includes the following steps: When there is only one first-level agent, a connection relationship is established between the first-level agent and the second-level agent. When there are at least two first-level agents, a connection relationship is established between the second-level agent and one of the first-level agents. Other first-level agents in the network to which the second-level agent belongs are dynamically discovered through the connected first-level agents. The secondary intelligent agent queries the service data and system status data of the local network element, generates an analysis report of the local network element based on the service data and system status data, and then sends the service data, system status data and analysis report to the primary intelligent agent. The first-level intelligent agent determines that a local network element is abnormal based on the analysis report, the business data, or the system status data, and adjusts the configuration information of the local network element.

2. The method according to claim 1, characterized in that, When the number of first-level agents is one, the connection relationship between the first-level agents and the second-level agents is constructed, including: In the secondary intelligent agent, the address information, symmetrically encrypted key, and certificate of the primary intelligent agent are statically configured; and in the primary intelligent agent, the address information, symmetrically encrypted key, and certificate of the secondary intelligent agent are statically configured. In the secondary intelligent agent, a request access message is generated based on the address information of the primary intelligent agent, the symmetric encrypted key, and the certificate, and the request access message is sent to the primary intelligent agent; the request access message also carries the device identifier, the network identifier, the intelligent agent identifier, the local network element type, and the local network element standard information of the secondary intelligent agent; In the first-level intelligent agent, the address information of the second-level intelligent agent, the symmetric encrypted key and certificate are verified and compared with the access request information based on the statically configured address information of the second-level intelligent agent; Once the verification is confirmed to be successful in the first-level intelligent agent, the second-level intelligent agent is connected to the first-level intelligent agent.

3. The method according to claim 2, characterized in that, After the secondary agent connects to the primary agent, the method further includes the following steps: The secondary agent sends a heartbeat packet to the primary agent for a first preset duration, and receives a response packet corresponding to the heartbeat packet returned by the primary agent.

4. The method according to claim 1, characterized in that, The step of dynamically discovering other first-level agents in the network to which the second-level agent belongs through the already connected first-level agents includes: The target first-level intelligent agent is securely connected to the first-level intelligent agent on the first-level intelligent agent discovery device. The target first-level intelligent agent includes a first-level intelligent agent connected to a second-level intelligent agent. The target first-level intelligent agent sends a dynamic discovery request to the first-level intelligent agent discovery device, and the dynamic discovery request carries the target first-level intelligent agent's own network information. The primary agent discovery device searches for a backup primary agent corresponding to its own network information based on the dynamic discovery request. Establish the connection relationship between the target first-level intelligent agent and the backup first-level intelligent agent.

5. The method according to claim 4, characterized in that, After the primary agent discovery device connects with the target primary agent, the method further includes the following steps: The first-level intelligent agent discovery device sends a heartbeat packet to the target first-level intelligent agent for a second preset time period, and receives a response packet corresponding to the heartbeat packet returned by the target first-level intelligent agent.

6. The method according to claim 1, characterized in that, The process of querying the service data and system status data of local network elements, and generating an analysis report for the local network elements based on the service data and system status data, includes: Query the business data and system status data of local network elements for the third preset time period; Based on the business data and the system status data, it is determined that the local network element is in an abnormal state, and an analysis report of the local network element is generated. The analysis report includes the anomaly point, the suspected anomaly point, and the data on which the anomaly analysis is based. Alternatively, based on the business data and the system status data, it can be determined that the local network element is not in an abnormal state, and an analysis report of the local network element can be generated, which includes identification information indicating that the local network element is in a normal state.

7. The method according to claim 1, characterized in that, The step of querying the service data and system status data of the local network element through the secondary intelligent agent, and generating an analysis report of the local network element based on the service data and system status data, includes: When a primary agent connected to the secondary agent receives a network analysis command, it sends a request for a network element analysis report to the secondary agent through the primary agent. The secondary intelligent agent queries the service data and system status data of the local network element according to the request network element analysis report instruction, and determines that the local network element has an abnormal state based on the service data and system status data, generating an analysis report of the local network element including anomaly points, suspected anomalies, and data on the basis for anomaly analysis; or, it determines that the local network element does not have an abnormal state based on the service data and system status data, generating an analysis report of the local network element including identification information indicating that the local network element is in a normal state.

8. The method according to claim 1, characterized in that, The step of determining that a local network element is abnormal based on the analysis report, the business data, or the system status data, and adjusting the configuration information of the local network element, includes: If an anomaly is determined in the corresponding local network element based on the analysis report, or if an anomaly is determined in the local network element based on all the service data or the system status data, a configuration modification operation message is sent to the secondary intelligent agent. In the secondary intelligent agent, the configuration modification operation of the local network element is performed according to the modified configuration operation information.

9. An electronic device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method as described in any one of claims 1 to 8.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 8.

Images