Network security auditing method and device for computing power driven intelligent agent of intelligent computing center cloud platform

Abstract

The invention provides a computing power driven agent network security auditing method and device for an intelligent computing center cloud platform, and relates to the technical field of intelligent computing centers, intelligent computing centers and computing power infrastructure, the method is executed by a first agent, and comprises the following steps: S1, sending broadcast information and receiving broadcast information sent by other agents; s2, updating a maintained routing table and an intelligent agent capability table according to the received broadcast information; s3, receiving a user task sent by the edge agent, decomposing the user task into a plurality of sub-tasks, selecting a second agent for executing the sub-tasks according to the maintained agent capability table and the routing table, and distributing the sub-tasks to the second agent; s4, receiving a subtask execution result, performing security audit on the subtask execution result, and if the subtask execution result does not pass the security audit, discarding or modifying the subtask execution result; and S5, generating a task execution result based on the subtask execution result passing the security audit, and sending the task execution result to the edge agent.

Description

Technical Field

[0001] The present invention relates to the technical fields of intelligent computing centers, intelligent computing centers, and computing power infrastructure, and particularly relates to a computing power-driven intelligent agent network security auditing method and device for an intelligent computing center cloud platform. Background Art

[0002] With the rapid development of artificial intelligence technology, "intelligent computing centers" and "intelligent computing centers" have emerged as the times require.

[0003] An "intelligent computing center" refers to a facility that uses large-scale heterogeneous computing power resources, including general computing power and intelligent computing power, to mainly provide the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios of artificial intelligence deep learning model development, model training, and model inference). An intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0004] The "intelligent computing center" includes but is not limited to the "intelligent computing center".

[0005] An "intelligent computing center", that is, an artificial intelligence computing center, is a type of computing power infrastructure based on artificial intelligence theory, adopting an artificial intelligence computing architecture, and providing computing power services, data services, and algorithm services required for artificial intelligence applications.

[0006] "Computing power" is the core of "intelligent computing centers" and "intelligent computing centers". It is the ability of computer devices or computing / data centers to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to achieve the output of target results through processing information data, and a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, which is mainly provided to society through computing power infrastructure.

[0007] Intelligent agents based on large language models or multi-modal large models have become the core components of the service ecosystem of intelligent computing centers. Intelligent computing centers provide powerful computing power support and resource scheduling capabilities for intelligent agents. The current intelligent agent technology is evolving from single intelligent agents to multi-agent systems to cope with complex task scenarios and distributed task processing requirements. In existing multi-agent systems, although a multi-agent cooperation mechanism is introduced, a centralized cooperation mechanism is generally adopted to manage the behaviors and resource allocations of all intelligent agents. Such a multi-agent system requires the topology map of intelligent agents to be determined at the system design stage and to be known to all participating intelligent agents. When the number of intelligent agents increases significantly and needs to adapt to complex tasks, the existing solutions lead to a lack of further dynamic expansion ability of the multi-agent system, easily form performance bottlenecks and increase the risk of failures, restricting the flexibility and robustness of the multi-agent system. In addition, how to audit the security of intelligent agents within a multi-agent system is also an urgent problem to be solved. Summary of the Invention

[0008] The present invention provides a computing power-driven intelligent agent network security auditing method and device for an intelligent computing center cloud platform, which are used to solve the problems that the existing multi-agent system adopting a centralized cooperation mechanism lacks further dynamic expansion ability, is prone to form a performance bottleneck and increase the failure risk, limits the flexibility and robustness of the multi-agent system, and how to audit the security of the intelligent agents in the multi-agent system.

[0009] To solve the above technical problems, the present invention is implemented as follows: In a first aspect, the present invention provides a computing power-driven intelligent agent network security auditing method for an intelligent computing center cloud platform, including: Step S1: The first intelligent agent sends broadcast information and receives the broadcast information sent by other intelligent agents. The broadcast information includes the ability information of the intelligent agent sending the broadcast information, the routing table and the intelligent agent ability table maintained by the intelligent agent sending the broadcast information; Step S2: The first intelligent agent updates the routing table and the intelligent agent ability table maintained by itself according to the received broadcast information; Step S3: When the first intelligent agent receives a user task sent by an edge intelligent agent, it decomposes the user task into multiple subtasks, selects a second intelligent agent for executing each subtask according to the intelligent agent ability table maintained by itself, and distributes the subtasks to the second intelligent agent according to the routing table maintained by itself; Step S4: The first intelligent agent receives the subtask execution results returned by the second intelligent agent, performs a security audit on the subtask execution results. If the subtask execution results do not pass the security audit, discard or modify the subtask execution results; Step S5: The first intelligent agent generates a task execution result based on the subtask execution results that pass the security audit, and sends the task execution result to the edge intelligent agent; Wherein, the routing table includes the third intelligent agent that the intelligent agent maintaining the routing table can reach, and the forwarding path between the intelligent agent and the third intelligent agent. The intelligent agent ability table includes the ability information of the third intelligent agent.

[0010] Optionally, the step S4 includes: Step S41: Perform at least one of the following security audits on the subtask execution results: Detect whether the subtask execution results contain inappropriate content. If it is detected that the subtask execution results contain the inappropriate content, determine that the subtask execution results do not pass the security audit; Detect whether the result of the subtask execution contains an unsafe prompt word. If it is detected that the result of the subtask execution contains the unsafe prompt word, determine that the result of the subtask execution fails the security audit; Detect whether the result of the subtask execution matches the intention of the subtask. If it is detected that the result of the subtask execution does not match the intention of the subtask, determine that the result of the subtask execution fails the security audit.

[0011] Optionally, step S3 includes: Step S3 includes: Step S31: For the target subtask among the multiple subtasks, the first agent selects multiple second agents to execute the target subtask, and sends the target subtask to the multiple second agents respectively according to the routing table maintained by itself; Step S4 includes: Step S41’: For the target subtask, the first agent performs a security audit on the subtask execution results returned by each second agent that executes the target subtask. If the subtask execution result fails the security audit, discard or modify the subtask execution result; if there are multiple subtask execution results that pass the security audit for the target subtask, select one subtask execution result from the multiple subtask execution results that pass the security audit as the subtask execution result of the target subtask.

[0012] Optionally, step S4 includes: Step S41’’: For the target subtask among the multiple subtasks, the first agent performs a security audit on the subtask execution results returned by the second agent. If the subtask execution result fails the security audit, discard the subtask execution result that fails the security audit, and reselect a second agent for the target subtask according to the agent capability table maintained by itself, and distribute the target subtask to the reselected second agent according to the routing table maintained by itself.

[0013] Optionally, step S3 includes: Step S31’: When the agent capability table maintained by the first agent contains multiple candidate agents with the same or similar capabilities, the first agent obtains the comprehensive value scores of the multiple candidate agents, and selects a second agent to execute the subtask from the multiple candidate agents according to the comprehensive value scores of the multiple candidate agents; Among them, the comprehensive value score is determined based on at least one of the following target indicators: computing power node performance indicators, network performance indicators, historical performance indicators, load status indicators, cost-benefit indicators, and security indicators. Among them, the security indicator is determined according to whether the subtask execution result historically returned by the candidate agent passes the security audit.

[0014] Optionally, the method further includes: Step S6: If it is detected that the subtask execution result returned by the second agent fails the security audit, the first agent reduces the score of the security indicator in the comprehensive value score of the second agent; Step S7: When the score of the security indicator in the comprehensive value score of the second agent is lower than the preset threshold, the first agent deletes the second agent from the agent capability table maintained by the first agent or adds the second agent to the blacklist.

[0015] In a second aspect, the present invention provides a security audit device for a computing power-driven agent network of an intelligent computing center cloud platform, including: A transceiver module, configured to send broadcast information and receive broadcast information sent by other agents. The broadcast information includes the capability information of the agent sending the broadcast information, the routing table and the agent capability table maintained by the agent sending the broadcast information; An update module, configured to update the routing table and the agent capability table maintained by itself according to the received broadcast information; A scheduling module, configured to, when receiving a user task sent by an edge agent, decompose the user task into multiple subtasks, select a second agent to execute each subtask according to the agent capability table maintained by itself, and distribute the subtasks to the second agent according to the routing table maintained by itself; A security audit module, configured to receive the subtask execution result returned by the second agent, perform a security audit on the subtask execution result, and discard or modify the subtask execution result if the subtask execution result fails the security audit; A feedback module, configured to generate a task execution result based on the subtask execution result that passes the security audit, and send the task execution result to the edge agent; Among them, the routing table includes the third agents that the agent maintaining the routing table can reach, and the forwarding paths between the third agents. The agent capability table includes the capability information of the third agents.

[0016] In a third aspect, the present invention provides an electronic device, including: a processor, a memory, and a program stored on the memory and executable on the processor. When the program is executed by the processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform as described in the first aspect above are implemented.

[0017] In a fourth aspect, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform as described in the first aspect above are implemented.

[0018] In a fifth aspect, the present invention provides a computer program product, including computer instructions. When the computer instructions are executed by a processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform as described in the first aspect above are implemented.

[0019] In the present invention, through a dynamic routing mechanism, the discovery and connection between intelligent agents are completed, thereby dynamically constructing a multi-intelligent agent system with a decentralized network. Intelligent agents can join or leave the network at any time without knowing the global topology in advance, enabling the multi-intelligent agent system to have the ability of dynamic expansion, reducing performance bottlenecks and failure risks, and greatly improving the flexibility and robustness of the multi-intelligent agent system. Furthermore, through the self-organizing cooperation mode between intelligent agents, the decomposition of complex tasks and the allocation of computing power resources are realized, so as to efficiently complete the processing of complex tasks. Further, by performing security audits on the execution results of subtasks returned by intelligent agents in the multi-intelligent agent system, the security and user experience of the multi-intelligent agent system are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of illustrating the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings: Figure 1 is a flowchart of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform of the present invention; Figure 2 is a structural diagram of the multi-intelligent agent system of the present invention; Figure 3 is a structural diagram of the computing power-driven intelligent agent network security auditing device of the intelligent computing center cloud platform of the present invention; Figure 4 is a structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The following will clearly and completely describe the technical solutions in the present invention in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the protection scope of the present invention.

[0022] First, the technical terms related to the present invention will be briefly described below.

[0023] The "computing power" described in the present invention refers to: the ability of a computer device or a computing / data center to process information, the ability of computer hardware and software to cooperate to jointly execute a certain computing requirement, the computing ability to achieve the output of a target result through processing information data, a new type of productive force integrating information computing power, network carrying capacity, and data storage capacity, and mainly providing services to society through computing power infrastructure.

[0024] The "computational power" (Computational Power, CP) described in the present invention refers to: the ability of a data center server to process data and achieve result output, a comprehensive index for measuring the computing ability of a data center, including general computing ability, supercomputing ability, and intelligent computing ability. The commonly used measurement unit is the number of floating-point operations per second (FLOPS, 1 EFLOPS = 10^18 FLOPS), and the larger the value, the stronger the comprehensive computing ability. It is estimated that 1 EFLOPS is approximately the computing power output of 5 Tianhe 2A or 500,000 mainstream server CPUs or 2 million mainstream laptops. The calculation formula is: CP = CP 通用 +CP 智能 +CP 超级 。

[0025] The "carrying capacity" (Network Power, NP) described in the present invention refers to: the performance of the data transmission ability of computing power facilities, a comprehensive ability including network architecture, network bandwidth, transmission delay, intelligent management and scheduling, etc., involving network transmission inside and between data centers, and a comprehensive index for measuring network transmission scheduling ability.

[0026] The "Storage Power" (SP) described in the present invention refers to the comprehensive ability of a data center in four aspects: data storage capacity, performance, security and reliability, and green and low-carbon. It is a comprehensive indicator for measuring the data storage capacity of a data center, including external storage devices such as storage arrays and built-in storage devices in servers. The commonly used measurement unit for storage capacity is exabyte (EB, 1EB = 2^60 bytes), the commonly used measurement unit for performance is the number of read / write operations per second per unit capacity (IOPS / TB, Input / Output Operations Per Second / TB), and the disaster recovery ratio is an important manifestation of security and reliability.

[0027] The "computing power infrastructure" described in the present invention refers to a new type of information infrastructure that integrates information computing power, network carrying capacity, and data storage power, and can realize the centralized computing, storage, transmission, and application of information.

[0028] The "new type of information infrastructure" described in the present invention mainly includes network infrastructures such as 5G networks, fiber broadband networks, backbone networks, international communication networks, and satellite Internet, computing power infrastructures such as data centers, general computing power centers, intelligent computing centers, and supercomputing centers, and new technology facilities such as artificial intelligence, blockchain, and quantum computing.

[0029] The "computing power" described in the present invention includes general computing power, intelligent computing power, and super computing power.

[0030] The "general computing power" described in the present invention refers to the computing power provided by servers based on CPU (Central Processing Unit) chips, which is used to support basic general computing such as cloud computing and edge computing.

[0031] The "intelligent computing power" described in the present invention refers to a computing platform that is scaled up for various artificial intelligence innovation applications based on dedicated chips such as GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), and ASIC (Application Specific Integrated Circuit), such as natural language processing, machine vision, and so on.

[0032] The "super computing power" described in the present invention mainly refers to the computing power provided by high-performance computing clusters such as supercomputers. It utilizes the centralized computing resources of multiple computer systems working in parallel and processes extremely complex or data-intensive problems through a dedicated operating system, and is mainly used for computing in cutting-edge scientific fields, such as planetary simulation, drug molecule design, gene analysis, etc.

[0033] The "Intelligent Computing Center" described in the present invention refers to a facility that uses large-scale heterogeneous computing power resources, including general computing power (CPU) and intelligent computing power (GPU, FPGA, ASIC, etc.), and mainly provides the required computing power, data, and algorithms for artificial intelligence applications (such as scenarios like artificial intelligence deep learning model development, model training, and model inference). The intelligent computing center covers facilities, hardware, and software, and can provide full-stack capabilities from underlying computing power to top-level application enabling.

[0034] The "Intelligent Computing Center Cloud Platform" described in the present invention refers to a cloud computing platform that comprehensively serves based on the hardware resources and software resources of the intelligent computing center.

[0035] The "Intelligent Computing Center" described in the present invention includes, but is not limited to, the "Intelligent Computing Center".

[0036] The "Intelligent Computing Center" described in the present invention, namely the artificial intelligence computing center, is a type of computing power infrastructure that is based on artificial intelligence theory, adopts an artificial intelligence computing architecture, and provides computing power services, data services, and algorithm services required for artificial intelligence applications.

[0037] The "Computing Power Center" described in the present invention refers to a facility mainly composed of infrastructure such as wind, fire, water, and electricity and IT software and hardware devices, and having computing power, carrying capacity, and storage capacity, including general data centers, intelligent computing centers, supercomputing centers, etc.

[0038] The "Supercomputing Center" described in the present invention, namely the supercomputing data center, is a data center based on supercomputers or large-scale computing clusters, which can provide functions such as large-scale computing, storage, and network services, and is widely used in application scenarios such as aerospace, national defense, oil exploration, climate modeling, and genome sequencing.

[0039] The "Computing Power Resources" described in the present invention refers to technologies and facilities with information computing, transmission, storage, and application capabilities required for the development of the digital society, including but not limited to computing resources such as CPU and GPU, network resources such as switches and routers, storage resources such as storage arrays and distributed storage, security resources such as firewalls and intrusion detection systems, and support and guarantee resources such as wind, fire, water, and electricity.

[0040] The "Computing Power Node" described in the present invention refers to the computing resources of servers / containers that can process computing tasks.

[0041] The "Large Language Model" described in the present invention refers to the large language model (LLM), which is a language model with a relatively large number of parameters, aiming to understand and generate human language, trained through a large amount of text data, and can perform a wide range of tasks including text summarization, translation, sentiment analysis, etc.

[0042] The "Multimodal Large Models" described in the present invention refer to models that jointly train multimodal information such as text, images, videos, and audio, including but not limited to multimodal large language models.

[0043] The "Agent" described in the present invention refers to an agent that can perceive the environment and take actions to achieve specific goals, and is an important part of the intelligent computing center cloud platform. It can be software, hardware, or a system, and has autonomy, adaptability, and interaction capabilities. The agent perceives changes in the environment (such as through sensors or data input), makes judgments and decisions based on the knowledge and algorithms it has learned, and then executes actions to affect the environment or achieve a predetermined goal. Agents are widely used in the field of artificial intelligence, and are commonly found in automation systems, robots, virtual assistants, and game characters. The core lies in the ability to learn independently and evolve continuously to better complete tasks and adapt to complex environments.

[0044] To solve the problems that the existing multi-agent system adopting a centralized cooperation mechanism lacks further dynamic expansion ability, is prone to form performance bottlenecks and increase the risk of failures, which limits the flexibility and robustness of the multi-agent system, and how to audit the security of agents within the multi-agent system, please refer to Figure 1 , the present invention provides a computing power-driven intelligent agent network security auditing method for an intelligent computing center cloud platform, and the method includes: Step S1: The first agent sends broadcast information and receives the broadcast information sent by other agents. The broadcast information includes the ability information of the agent sending the broadcast information, the routing table maintained by the agent sending the broadcast information, and the agent ability table. In the present invention, optionally, the first agent includes at least one of the following: an agent deployed inside the intelligent computing center; an agent deployed outside the intelligent computing center. That is to say, the first agent can be an agent deployed inside the intelligent computing center or an agent deployed outside the intelligent center.

[0045] The first agent sends broadcast information to other agents. The broadcast information sent by the first agent includes: the ability information of the first agent, the routing table maintained by the first agent, and the agent ability table. Among them, the routing table sent by the first agent contains the third agent that the first agent can reach and the forwarding path between the first agent and the third agent. The agent ability table sent by the first agent contains the ability information of the third agent.

[0046] In the present invention, the capability information of the agent is stored in a preset data table in the form of a structured description statement. The capability scope of the agent covers two levels: basic function capabilities and business application capabilities. The basic function capabilities include, but are not limited to: document parsing and processing capabilities, code generation and analysis capabilities, image recognition and processing capabilities, and multi-modal information processing capabilities. The business application capabilities include, but are not limited to: specialized processing capabilities for specific business scenarios such as life scenarios and financial data scenarios.

[0047] In the present invention, the third agent refers to the destination node in the routing table, and the forwarding path between the first agent and the third agent refers to the forwarding path for the information sent by the first agent to reach the third agent.

[0048] Optionally, the first agent periodically sends broadcast information. The sending period can be set as needed.

[0049] The first agent can also receive broadcast information sent by other agents. The broadcast information sent by other agents includes: the capability information of the other agents, the routing table and the agent capability table maintained by the other agents. Among them, the routing table sent by other agents contains the third agents that the other agents can reach, and the forwarding paths between the other agents and the third agents. The agent capability table sent by other agents contains the capability information of the third agents.

[0050] In the present invention, the third agent refers to the destination node in the routing table, and the forwarding path between other agents and the third agent refers to the forwarding path for the information sent by other agents to reach the third agent.

[0051] In the present invention, the first agent receives broadcast information sent by adjacent other agents. It should be noted that in the present invention, adjacent agents can be connected by a wired method or by a wireless method.

[0052] Optionally, the other agents periodically send broadcast information. The sending period can be set as needed. Further optionally, the sending periods of each agent (i.e., including the above-mentioned first agent and other agents) can be the same.

[0053] In the present invention, optionally, the other agents include at least one of the following: An agent deployed in the first intelligent computing center, where the first intelligent computing center is the intelligent computing center to which the first agent belongs; An agent deployed in the second intelligent computing center; An agent deployed outside the intelligent computing center.

[0054] The routing table in the present invention can be seen in Table 1 shown below. Table 1 is the routing table maintained by Agent A.

[0055] Table 1

[0056] The agent capability table in the present invention can be seen in Table 2 shown below. Table 2 is the agent capability table maintained by Agent A.

[0057] Table 2

[0058] Agent A can be the above-mentioned first agent or the above-mentioned other agents.

[0059] In the present invention, as shown in Table 3, the routing table and the agent capability table can also be integrated into one table.

[0060] Table 3

[0061] It should be noted that the formats of the above-mentioned routing table and agent capability table are only examples and can also be other formats.

[0062] Step S2: The first agent updates the routing table and the agent capability table it maintains according to the received broadcast information; In the present invention, after the first agent receives the broadcast information sent by other agents, it can query whether the identities of the other agents are included in the routing table and the agent capability table it maintains. If not, it is necessary to add the identities of the other agents to the routing table and the agent capability table, and at the same time generate a forwarding path between the first agent and the other agents in the routing table, and record the capability information of the other agents in the agent capability table. In addition, it is also necessary to determine, according to the routing tables of all the other agents, the agents that the first agent can reach through the relay of the other agents, and the forwarding paths between the first agent and the agents that can be reached through the relay of the other agents, and update them to the routing table maintained by the first agent. At the same time, update the capability information of the agents that can be reached through the relay of the other agents to the agent capability table maintained by the first agent.

[0063] If the identities of the other agents are included in the routing table and the agent capability table it maintains, the first agent also needs to update the forwarding paths between itself and the other agents, as well as the forwarding paths between itself and the agents that can be reached through the relay of the other agents in the routing table it maintains. At the same time, it also needs to update the capability information of the other agents and the agents that can be reached through the relay of the other agents recorded in the agent capability table it maintains.

[0064] So far, through the above dynamic routing mechanism, the agents can discover and connect with each other, thereby dynamically constructing a multi-agent system with a decentralized network.

[0065] Please refer to Figure 2 , Figure 2 , which is a schematic structural diagram of the multi-agent system of the present invention. Figure 2 In, each agent (A, B, C...) respectively maintains its own routing table and agent capability table, and periodically sends broadcast information. The agent that receives the broadcast information needs to update the routing table and agent capability table maintained by itself based on the received broadcast information to complete the discovery and connection between agents. The above first agent can be Figure 2 any agent in.

[0066] Figure 2 In, the intelligent computing center 1 and the intelligent computing center 2 respectively include a plurality of internal agents. At the same time, it can also include aggregable external agents. Among them, the agent K is an aggregable external agent of the intelligent computing center 1, and the agents I and J are aggregable external agents of the intelligent computing center 2. The "aggregable external agent" described in the present invention refers to an agent deployed outside the intelligent computing center and capable of collaborating with the agents inside the intelligent computing center to complete tasks.

[0067] The above agents include three main modules. One module is the routing module, which is used to send and receive broadcast information and maintain the routing table; the capability information module, which is used to determine its own capability information and maintain the agent capability table; the task execution module, which is used to execute tasks. In addition, some agents may also have a task decomposition module for performing task decomposition. Some agents may also have a security audit module for performing security audits.

[0068] Step S3: When the first agent receives the user task sent by the edge agent, it decomposes the user task into multiple subtasks, and based on the agent capability table maintained by itself, selects the second agent for executing each subtask, and distributes the subtasks to the second agent according to the routing table maintained by itself; It should be noted that the first agent in the present invention is an agent with the ability of task decomposition and computing power resource allocation, and can be any agent in the above constructed decentralized network. Preferably, considering security and computing power capabilities, it can be an agent inside the intelligent computing center. Further preferably, it is an agent inside the intelligent computing center that plays a role in connecting with external agents, such as Figure 2Agent A and Agent F in it. In the present invention, optionally, an agent for task decomposition and computing power resource allocation can be set for each intelligent computing center.

[0069] In the present invention, the edge agent can be deployed at the network edge or on the user side, and is responsible for the access and preliminary processing of user tasks.

[0070] In an optional manner, when the edge agent receives a user task sent by a user, it can directly forward the user task to the first agent. In this case, the edge agent can select the first agent in various ways. For example, it can select the agent inside the intelligent computing center closest to it as the first agent, or select the agent inside the intelligent computing center with the lowest cost as the first agent, etc.

[0071] In another optional manner, when the edge agent receives a user task sent by a user, it can preprocess the user task. The preprocessing is, for example, to evaluate the capabilities required by the user task, so as to select the first agent that matches the capabilities of the user task, or select the intelligent computing center that matches the capabilities of the user task. Or, the edge agent can also perform a preliminary decomposition of the user task.

[0072] In the present invention, the edge agent needs to query the routing table maintained by itself, and send the user task to the first agent according to the forwarding path between the first agent selected and the one queried from the routing table.

[0073] In the present invention, the first agent can decompose the user task into multiple subtasks that can be independently executed. The multiple subtasks can include multiple subtasks that can be executed simultaneously, or can also include subtasks that need to wait for other subtasks to be executed before they can be executed. The first agent determines the agent capabilities required for each subtask, and selects the second agent that executes each of the subtasks from the maintained agent capability table. Among them, each second agent can execute one subtask or multiple subtasks. Or, one subtask can also be executed simultaneously by multiple second agents. The first agent distributes the subtasks to the corresponding second agents according to the maintained routing table.

[0074] Step S4: The first agent receives the subtask execution result returned by the second agent, performs a security audit on the subtask execution result. If the subtask execution result fails the security audit, discard or modify the subtask execution result; Step S5: The first agent generates a task execution result based on the subtask execution results that have passed the security audit, and sends the task execution result to the edge agent; In the present invention, if the execution result of a subtask is modified, it can be considered that the modified execution result of the subtask has passed the security audit, or, after modifying the execution result of the subtask, the security audit is performed on the execution result of the subtask again.

[0075] According to specific circumstances, the first agent may merge the execution results of subtasks returned by multiple second agents to obtain the task execution result, or analyze the execution results of subtasks returned by multiple second agents to obtain the task execution result.

[0076] The first agent sends the task execution result to the edge agent according to the query routing table and the forwarding path between the first agent and the edge agent in the routing table.

[0077] Among them, the routing table (including the routing table of the above-mentioned first agent and the routing tables of other agents) contains the third agents that the agent maintaining the routing table can reach, and the forwarding paths between the third agents. The agent capability table contains the capability information of the third agents.

[0078] In the present invention, through the dynamic routing mechanism, the agents discover and connect to each other, thereby dynamically constructing a multi-agent system with a decentralized network. Agents can join or leave the network at any time without the need to know the global topology structure, enabling the multi-agent system to have the ability of dynamic expansion, reducing performance bottlenecks and failure risks, and greatly improving the flexibility and robustness of the multi-agent system. Furthermore, through the self-organizing cooperation mode between agents, the decomposition of complex tasks and the allocation of computing power resources are realized, so as to efficiently complete the processing of complex tasks. Further, by performing security audits on the execution results of subtasks returned by agents in the multi-agent system, the security and user experience of the multi-agent system are improved.

[0079] It should be noted that the agents in the present invention are agents based on large language models or multi-modal large models. The term "based on large language models or multi-modal large models" means that by organizing input information and designing prompt words, large language models or multi-modal large models are called to perform tasks such as reasoning, design, dialogue with users, generating solution designs, and / or code generation.

[0080] In the present invention, optionally, the step S4 includes: Step S41: Perform at least one of the following security audits on the execution result of the subtask: (1) Detect whether the execution result of the subtask contains inappropriate content. If it is detected that the execution result of the subtask contains the inappropriate content, determine that the execution result of the subtask fails the security audit; Among them, inappropriate content may include content that does not match the user's age, etc. For example, if it is recognized that the user task is to develop an English learning course for children under 6 years old, and the sub-task execution result includes content such as game advertisements, it is considered that there is inappropriate content.

[0081] When there is inappropriate content in the sub-task execution result, the sub-task execution result can be directly discarded, or alternatively, the sub-task execution result can be modified, such as filtering out the inappropriate content.

[0082] (2) Detect whether the sub-task execution result contains unsafe prompt words. If it is detected that the sub-task execution result contains the unsafe prompt words, determine that the sub-task execution result fails the security audit; This article is mainly used to prevent the second intelligent agent from attacking the first intelligent agent by sending unsafe prompt words to the first intelligent agent. For example, the second intelligent agent obtains the privacy data of the first intelligent agent by sending prompt words, or modifies the task command of the first intelligent agent, or replaces the role of other intelligent agents, etc.

[0083] When there are unsafe prompt words in the sub-task execution result, the sub-task execution result can be directly discarded.

[0084] (3) Detect whether the sub-task execution result matches the intention of the sub-task. If it is detected that the sub-task execution result does not match the intention of the sub-task, determine that the sub-task execution result fails the security audit.

[0085] In the present invention, optionally, when the first intelligent agent decomposes the user task into multiple sub-tasks, it can identify the intention of the sub-task. After the second intelligent agent returns the sub-task execution result, it detects whether the sub-task execution result matches the intention of the sub-task. If it is detected that the sub-task execution result does not match the intention of the sub-task, it means that the deviation degree between the sub-task execution result and the intention of the sub-task is too high, and it is determined that the sub-task execution result fails the security audit, and the sub-task execution result can be directly discarded.

[0086] In the present invention, optionally, the step S3 includes: Step S31: For the target sub-task among the multiple sub-tasks, the first intelligent agent selects multiple second intelligent agents to execute the target sub-task, and sends the target sub-task to the multiple second intelligent agents respectively according to the routing table maintained by itself; That is to say, for one sub-task, multiple second intelligent agents can be selected to execute.

[0087] The target subtask may be a part of the multiple subtasks. For each subtask in this part, multiple second agents correspond to each subtask. For some other subtasks, one second agent may correspond to one subtask.

[0088] The target subtask may also be all the subtasks, that is, multiple second agents correspond to each subtask among the multiple subtasks.

[0089] Step S4 includes: Step S41': For the target subtask, the first agent performs a security audit on the subtask execution results returned by each second agent executing the target subtask. If the subtask execution result fails the security audit, discard or modify the subtask execution result; if there are multiple subtask execution results that pass the security audit for the target subtask, select one subtask execution result from the multiple subtask execution results that pass the security audit as the subtask execution result of the target subtask.

[0090] In the present invention, one subtask execution result can be selected from multiple subtask execution results that pass the security audit as the subtask execution result of the target subtask according to the matching degree between the subtask execution result and the intention. For example, select the subtask execution result with the highest matching degree with the intention of the target subtask.

[0091] Optionally, in the present invention, step S4 includes: Step S41'': For the target subtask among the multiple subtasks, the first agent performs a security audit on the subtask execution results returned by the second agent. If the subtask execution result fails the security audit, discard the subtask execution result that fails the security audit, and reselect a second agent for the target subtask according to the agent capability table maintained by itself, and distribute the target subtask to the reselected second agent according to the routing table maintained by itself.

[0092] It should be noted that steps S41, S41', S41'', etc. in the present invention are only used to illustrate different steps and do not represent the order between the steps.

[0093] Optionally, in the present invention, step S3 includes: Step S31': When there are multiple candidate agents with the same or similar capabilities in the agent capability table maintained by the first agent, obtain the comprehensive value scores of the multiple candidate agents, and select a second agent to execute the subtask from the multiple candidate agents according to the comprehensive value scores of the multiple candidate agents; wherein, the comprehensive value scores are determined based on at least one of the following target metrics: computing power node performance, network performance metrics, historical performance metrics, load status metrics, cost-benefit metrics, security metrics, and the security metrics are determined according to whether the subtask execution results historically returned by the candidate agent pass the security audit.

[0094] Among them, the computing power node performance may include at least one of the following: hardware metrics such as CPU performance, GPU performance, memory capacity, storage speed, etc.; The network performance metrics may include at least one of the following: connection quality metrics such as access latency, bandwidth capacity, network stability, etc.; The historical performance metrics may include at least one of the following: historical task completion success rate, historical task processing quality, etc.; The load status metrics may include at least one of the following: load condition, available resource margin, etc.; The cost-benefit metrics may include at least one of the following: usage cost, cost performance of expected revenue, etc.

[0095] In the present invention, optionally, the comprehensive value score is the weighted sum of at least two of the above target metrics, that is, the comprehensive value of the agent is evaluated from multiple dimensions.

[0096] In the present invention, optionally, select the agent with the highest comprehensive value score as the second agent.

[0097] In the present invention, optionally, the above process of selecting the second agent may be carried out for a certain subtask. For example, for a certain subtask, multiple candidate agents with the same or similar capabilities are queried from the agent capability table. At this time, it is necessary to select the agent with the highest comprehensive value score as the second agent.

[0098] The above process of selecting the second agent may also be carried out for multiple subtasks simultaneously. For example, when multiple subtasks all require the same or similar agents to execute, and multiple candidate agents with the same or similar capabilities are queried from the agent capability table, and the number of candidate agents is more than the number of subtasks, at this time, multiple agents with the highest comprehensive value scores can be selected from the queried candidate agents as the second agents, respectively used to process the multiple subtasks.

[0099] In the present invention, optionally, step S3 further includes: Step S31'': The first agent collects the target metrics of each agent in the agent capability table it maintains, and calculates the comprehensive value scores of each agent in the agent capability table it maintains based on the collected target metrics. In the present invention, optionally, the first agent may periodically collect the target metrics of each agent in the agent capability table it maintains, calculate the comprehensive value scores of each agent in the agent capability table it maintains, and record the comprehensive value scores of each agent in the agent capability table it maintains, so as to facilitate querying.

[0100] The first agent may also, when a user task needs to be executed, collect the target metrics of each agent in the agent capability table it maintains in real time, and calculate the comprehensive value scores of each agent in the agent capability table it maintains, so that the collected target metrics are more real-time.

[0101] It should be noted that steps S31, S31', S31'' etc. in the present invention are only used to illustrate different steps and do not represent the order between the steps.

[0102] In the present invention, optionally, the method further includes: Step S6: If it is detected that the sub-task execution result returned by the second agent fails the security audit, the first agent reduces the score of the security metric in the comprehensive value score of the second agent. For example, every time it is detected that the sub-task execution result returned by the second agent fails the security audit, the score of the security metric in the comprehensive value score of the second agent is reduced by a preset score.

[0103] Step S7: When the score of the security metric in the comprehensive value score of the second agent is lower than a preset threshold, the first agent deletes the second agent from the agent capability table maintained by the first agent or adds the second agent to the blacklist.

[0104] Adding the second agent to the blacklist means that the second agent will no longer be added to the agent capability table maintained by the first agent in the future. However, deleting the second agent from the agent capability table maintained by the first agent means that the second agent may be added to the agent capability table maintained by the first agent again in the future.

[0105] In the present invention, optionally, before the step S1, the method further includes: Step S0: The first agent determines the capability information. Wherein, when the first agent is an agent for task decomposition and allocation within the first intelligent computing center, the capability information determined by the first agent includes the capability information of all agents that can be aggregated by the first intelligent computing center to which the first agent belongs.

[0106] For example, please refer to Figure 2 , assuming the first agent is Agent A, the capability information determined by Agent A includes the capability information of all agents that can be aggregated by Intelligent Computing Center 1, that is, the capability information of Intelligent Computing Center 1 as a whole, including the capability information of Agents A, B, C, and K. Assuming the first agent is Agent F, the capability information determined by Agent F includes the capability information of all agents that can be aggregated by Intelligent Computing Center 2, that is, the capability information of Intelligent Computing Center 2 as a whole, including the capability information of Agents F, G, H, I, and J.

[0107] However, the capabilities determined by other agents except for the agents for task decomposition and allocation are their own capabilities. For example, Figure 2 the capability information determined by Agent B in

[0108] is its own capability information. Please refer to Figure 3 , the present invention also provides a computing power-driven intelligent agent network security auditing device 10 for an intelligent computing center cloud platform, including: A transceiver module 11 for sending broadcast information and receiving broadcast information sent by other agents. The broadcast information includes the capability information of the agent sending the broadcast information, the routing table maintained by the agent sending the broadcast information, and the agent capability table. An update module 12 for updating the routing table and the agent capability table maintained by itself according to the received broadcast information. A scheduling module 13 for, when receiving a user task sent by an edge agent, decomposing the user task into multiple subtasks, selecting a second agent for executing each subtask according to the agent capability table maintained by itself, and distributing the subtasks to the second agent according to the routing table maintained by itself. A security auditing module 14 for receiving the subtask execution results returned by the second agent, performing security auditing on the subtask execution results, and discarding or modifying the subtask execution results if the subtask execution results fail the security auditing. A feedback module 15 for generating a task execution result based on the subtask execution results that pass the security auditing and sending the task execution result to the edge agent. Among them, the routing table contains the third agents that the agent maintaining the routing table can reach, and the forwarding paths between the agent and the third agents, and the agent capability table contains the capability information of the third agents.

[0109] In the present invention, through the dynamic routing mechanism, the agents discover and connect with each other, thereby dynamically constructing a multi-agent system with a decentralized network. Agents can join or leave the network at any time without knowing the global topology in advance, enabling the multi-agent system to have the ability of dynamic expansion, reducing performance bottlenecks and failure risks, and greatly improving the flexibility and robustness of the multi-agent system. Furthermore, through the self-organizing cooperation mode between agents, the decomposition of complex tasks and the allocation of computing power resources are realized, so as to efficiently complete the processing of complex tasks. Further, by performing security audits on the execution results of sub-tasks returned by agents in the multi-agent system, the security and user experience of the multi-agent system are improved.

[0110] Optionally, the first agent includes at least one of the following: An agent deployed inside the intelligent computing center; An agent deployed outside the intelligent computing center; And / or, the other agents include at least one of the following: An agent deployed in the first intelligent computing center, where the first intelligent computing center is the intelligent computing center to which the first agent belongs; An agent deployed in the second intelligent computing center; An agent deployed outside the intelligent computing center.

[0111] Optionally, the security audit module 14 is used to perform at least one of the following security audits on the execution results of the sub-tasks: Detect whether the execution result of the sub-task contains inappropriate content. If it is detected that the execution result of the sub-task contains the inappropriate content, it is determined that the execution result of the sub-task fails the security audit; Detect whether the execution result of the sub-task contains insecure prompt words. If it is detected that the execution result of the sub-task contains the insecure prompt words, it is determined that the execution result of the sub-task fails the security audit; Detect whether the execution result of the sub-task matches the intention of the sub-task. If it is detected that the execution result of the sub-task does not match the intention of the sub-task, it is determined that the execution result of the sub-task fails the security audit.

[0112] Optionally, the scheduling module 13 is configured to select multiple second agents for executing a target subtask among the multiple subtasks, and send the target subtask to the multiple second agents respectively according to the routing table maintained by itself; The security audit module 14 is configured to perform a security audit on the subtask execution results returned by each second agent for the target subtask. If the subtask execution result fails the security audit, discard or modify the subtask execution result; if there are multiple subtask execution results that pass the security audit for the target subtask, select one subtask execution result from the multiple subtask execution results that pass the security audit as the subtask execution result of the target subtask.

[0113] Optionally, the security audit module 14 is configured to perform a security audit on the subtask execution results returned by the second agent for the target subtask among the multiple subtasks. If the subtask execution result fails the security audit, discard the subtask execution result that fails the security audit, and re-select a second agent for the target subtask according to the agent capability table maintained by itself, and distribute the target subtask to the re-selected second agent according to the routing table maintained by itself.

[0114] Optionally, the scheduling module 13 includes: A selection sub-module, configured to obtain a comprehensive value score of the multiple candidate agents when the agent capability table maintained by the first agent includes multiple candidate agents with the same or similar capabilities, and select a second agent for executing the subtask from the multiple candidate agents according to the comprehensive value score of the multiple candidate agents; wherein, the comprehensive value score is determined based on at least one of the following target metrics: computing power node performance metric, network performance metric, historical performance metric, load status metric, cost-benefit metric, security metric, and the security metric is determined according to whether the subtask execution results historically returned by the candidate agent pass the security audit.

[0115] Optionally, the comprehensive value score is the weighted sum of at least two of the target metrics.

[0116] Optionally, the scheduling module 13 includes: A calculation sub-module, configured to collect the target metrics of each agent in the agent capability table maintained by it, and calculate the comprehensive value score of each agent in the agent capability table maintained by it according to the collected target metrics.

[0117] Optionally, the device further includes: The comprehensive value score update module is used to reduce the score of the security index in the comprehensive value score of the second agent if it is detected that the subtask execution result returned by the second agent fails the security audit. The processing module is used to delete the second agent from the agent capability table maintained by the first agent or add the second agent to the blacklist when the score of the security index in the comprehensive value score of the second agent is lower than the preset threshold.

[0118] Optionally, the device further includes: The determination module is used to determine the capability information; wherein, when the first agent is an agent for task decomposition and allocation in the first intelligent computing center, the capability information determined by the first agent includes the capability information of all agents that can be aggregated by the first intelligent computing center to which the first agent belongs.

[0119] Please refer to Figure 4 , the present invention also provides an electronic device 20, including a processor 21, a memory 22, and a computer program stored on the memory 22 and executable on the processor 21. When the computer program is executed by the processor 21, it implements each process of the foregoing embodiment of the method for power-driven agent network security audit of the intelligent computing center cloud platform, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0120] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements each process of the foregoing embodiment of the method for power-driven agent network security audit of the intelligent computing center cloud platform, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here. Among them, the computer-readable storage medium is, for example, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc, etc.

[0121] The present invention also provides a computer program product, including computer instructions, which when executed by a processor, implement each process of the foregoing Figure 1 shown embodiment of the method for power-driven agent network security audit of the intelligent computing center cloud platform, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0122] It should be noted that in this text, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements not only includes those elements but also other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, article or device comprising such element.

[0123] From the description of the above embodiments, those skilled in the art can clearly understand that the above-described embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions for causing a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0124] The embodiments of the present invention have been described above in conjunction with the accompanying drawings. However, the present invention is not limited to the above specific embodiments. The above specific embodiments are merely illustrative and not restrictive. Under the inspiration of the present invention, those of ordinary skill in the art can also make many forms without departing from the purpose of the present invention and the scope protected by the claims, and all of them fall within the protection scope of the present invention.

Claims

1. A computing power-driven intelligent agent network security auditing method for an intelligent computing center cloud platform, characterized in that, Including: Step S1: The first agent sends broadcast information and receives the broadcast information sent by other agents. The broadcast information includes the capability information of the agent sending the broadcast information, the routing table maintained by the agent sending the broadcast information, and the agent capability table. Step S2: The first agent updates the routing table and the agent capability table it maintains according to the received broadcast information. Step S3: When the first agent receives a user task sent by an edge agent, it decomposes the user task into multiple subtasks, selects a second agent to execute each subtask according to the agent capability table it maintains, and distributes the subtasks to the second agent according to the routing table it maintains. Step S4: The first agent receives the subtask execution results returned by the second agent, conducts a security audit on the subtask execution results. If the subtask execution results do not pass the security audit, discard or modify the subtask execution results. Step S5: The first agent generates a task execution result based on the subtask execution results that pass the security audit, and sends the task execution result to the edge agent. Wherein, the routing table includes the third agents that the agent maintaining the routing table can reach, and the forwarding paths between the third agents. The agent capability table includes the capability information of the third agents.

2. The method according to claim 1, wherein The step S4 includes: Step S41: Conduct at least one of the following security audits on the subtask execution results: Detect whether the subtask execution results contain inappropriate content. If it is detected that the subtask execution results contain the inappropriate content, determine that the subtask execution results do not pass the security audit. Detect whether the subtask execution results contain insecure prompt words. If it is detected that the subtask execution results contain the insecure prompt words, determine that the subtask execution results do not pass the security audit. Detect whether the subtask execution results match the intention of the subtask. If it is detected that the subtask execution results do not match the intention of the subtask, determine that the subtask execution results do not pass the security audit.

3. The method according to claim 1, wherein: The step S3 includes: Step S31: For a target subtask among the multiple subtasks, the first agent selects multiple second agents to execute the target subtask, and sends the target subtask to the multiple second agents respectively according to the routing table it maintains. The step S4 includes: Step S41’: For the target subtask, the first agent conducts a security audit on the subtask execution results returned by each second agent executing the target subtask. If the subtask execution results do not pass the security audit, discard or modify the subtask execution results. If there are multiple subtask execution results that pass the security audit for the target subtask, select one subtask execution result from the multiple subtask execution results that pass the security audit as the subtask execution result of the target subtask.

4. The method according to claim 1, wherein The step S4 includes: Step S41'': For the target subtask among the multiple subtasks, the first agent performs a security audit on the subtask execution result returned by the second agent. If the subtask execution result fails the security audit, discard the subtask execution result that fails the security audit, and based on the agent capability table maintained by itself, reselect a second agent for the target subtask, and distribute the target subtask to the reselected second agent according to the routing table maintained by itself.

5. The method according to claim 1, wherein The step S3 includes: Step S31': When there are multiple candidate agents with the same or similar capabilities in the agent capability table maintained by the first agent, the first agent obtains the comprehensive value scores of the multiple candidate agents, and selects a second agent to execute the subtask from the multiple candidate agents according to the comprehensive value scores of the multiple candidate agents; Among them, the comprehensive value score is determined based on at least one of the following target metrics: computing power node performance metric, network performance metric, historical performance metric, load status metric, cost-benefit metric, security metric, where the security metric is determined according to whether the subtask execution result historically returned by the candidate agent passes the security audit.

6. The method according to claim 5, characterized in that It also includes: Step S6: If it is detected that the subtask execution result returned by the second agent fails the security audit, the first agent reduces the score of the security metric in the comprehensive value score of the second agent; Step S7: When the score of the security metric in the comprehensive value score of the second agent is lower than the preset threshold, the first agent deletes the second agent from the agent capability table maintained by the first agent or adds the second agent to the blacklist.

7. A computing power-driven intelligent agent network security auditing device for an intelligent computing center cloud platform, characterized in that, It includes: A transceiver module, configured to send broadcast information and receive broadcast information sent by other agents, where the broadcast information includes the capability information of the agent sending the broadcast information, the routing table and the agent capability table maintained by the agent sending the broadcast information; An update module, configured to update the routing table and the agent capability table maintained by itself according to the received broadcast information; A scheduling module, configured to, when receiving a user task sent by an edge agent, decompose the user task into multiple subtasks, select a second agent to execute each subtask according to the agent capability table maintained by itself, and distribute the subtask to the second agent according to the routing table maintained by itself; A security audit module, configured to receive the subtask execution result returned by the second agent, perform a security audit on the subtask execution result, and if the subtask execution result fails the security audit, discard or modify the subtask execution result; A feedback module, configured to generate a task execution result based on the subtask execution result that passes the security audit, and send the task execution result to the edge agent; Among them, the routing table includes the third agents that the agent maintaining the routing table can reach, and the forwarding paths between the third agents, and the agent capability table includes the capability information of the third agents.

8. An electronic device, characterized in that, It includes: A processor, a memory, and a program stored on the memory and executable on the processor, wherein when the program is executed by the processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform according to any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that, It includes computer instructions, and when the computer instructions are executed by a processor, the steps of the computing power-driven intelligent agent network security auditing method of the intelligent computing center cloud platform according to any one of claims 1 to 6 are implemented.

Images