Multi-agent collaborative wireless network optimization solution recommendation method

Abstract

The present application provides a method for recommending a multi-agent collaborative wireless network optimization solution. Applied to the field of wireless network communication technology, the method includes a project manager agent starting an optimization project; a data collection agent collecting data to be processed; a road test management agent collecting road test data; a network optimization expert agent performing network diagnosis on the data to be processed and obtaining a diagnosis result; a network optimization expert agent obtaining a preliminary optimization solution based on the diagnosis result; a test and verification agent performing performance and stability tests on the preliminary optimization solution, obtaining a test report, and feeding it back to the network optimization expert agent; a network optimization expert agent evaluating the test report, obtaining an intermediate optimization solution, and feeding the intermediate optimization solution back to the project manager agent, so that the project manager agent can output the final optimization solution. In this way, the accuracy of recommending wireless network optimization solutions can be improved.

Description

Technical Field

[0001] The present disclosure relates to the field of wireless network communication technology, and in particular to a method for recommending a multi-agent collaborative wireless network optimization solution. Background Art

[0002] The current large-scale deployment of 5G networks, the coexistence of four generations of networks, and the surge in user demand have significantly increased the complexity of network optimization. A multi-agent system refers to a collection of multiple agents (intelligent agents) with autonomous decision-making, learning and communication capabilities. These agents can collaborate with each other to complete tasks or solve problems together. This system can effectively handle complex problems through information interaction and collaborative work between agents, and is particularly suitable for application scenarios that require distributed decision-making, real-time response and high flexibility. Multi-agent systems play an increasingly important role in wireless network optimization. By introducing multi-agents, each agent can make independent decisions based on its own environment and status, thereby improving the flexibility and robustness of the network; in wireless networks, user needs and environmental changes are often dynamic, and agents can perceive network status in real time and respond quickly to changes, optimize resource allocation, and ensure optimal network performance; through information sharing and collaboration between agents, efficient use of network resources can be achieved, and delays and interference can be reduced; the optimization problems of wireless networks are usually highly nonlinear and complex, and multi-agent systems can solve these complex optimization problems through a divide-and-conquer strategy, thereby improving the overall performance of the network and user experience.

[0003] At present, on the one hand, existing wireless network optimization methods are usually based on static models or the decisions of a single expert, which are difficult to adapt to the rapidly changing network environment, and the optimization effect is limited. In addition, the optimization solutions provided lack explainability and are difficult to be recognized by front-line personnel. On the other hand, they do not involve the most cutting-edge AI technology of large model (LLM) + intelligent agent, and cannot provide flexible network optimization API tool library calls, which leads to low accuracy in recommending wireless network optimization solutions. Summary of the invention

[0004] The present disclosure provides a method for recommending a multi-agent collaborative wireless network optimization solution.

[0005] According to a first aspect of the present disclosure, a method for recommending a multi-agent collaborative wireless network optimization solution is provided. The method comprises:

[0006] A number of multi-agent roles are set up on a collaborative framework that supports large-model agents; the multi-agent roles include at least a project manager agent, a data collection agent, a network optimization expert agent, a manual intervention agent, a road test management agent, a test and verification agent, and a programming engineer agent; the project manager agent and the programming engineer agent are both configured with a general large model; the data collection agent, the network optimization expert agent, the manual intervention agent, the road test management agent, and the test and verification agent are all configured with a communication network large model; the communication network large model is obtained by training the general large model according to the proprietary knowledge of the communication industry; the programming engineer agent has Python programming ability and is familiar with graph database and relational database operations;

[0007] The project manager agent starts the optimization project based on the user's service request details or low-perception work orders, and sends collection instructions to the data collection agent;

[0008] The data collection agent collects the data to be processed from the network equipment and the user equipment according to the collection instruction, and sends the data to be processed to the network optimization expert agent and the test and verification agent;

[0009] The drive test management agent collects the drive test data and sends it to the network optimization expert agent;

[0010] The network optimization expert agent performs network diagnosis on the data to be processed according to the diagnosis instruction sent by the project manager agent and the road test data to obtain a diagnosis result; the network optimization expert agent obtains a preliminary optimization plan according to the diagnosis result;

[0011] The testing and verification agent performs performance and stability tests on the preliminary optimization scheme, obtains a test report, and feeds back the test report to the network optimization expert agent;

[0012] The network optimization expert agent evaluates the test report to obtain an intermediate optimization solution, and feeds the intermediate optimization solution back to the project manager agent so that the project manager agent can output a final optimization solution.

[0013] Further: the data collection agent is at least configured with a network data base API interface access tool and a user data API interface access tool;

[0014] The network optimization expert agent is configured with at least a network optimization knowledge graph API access tool, a rule engine API access tool, and an AI diagnosis algorithm API access tool;

[0015] The drive test management agent is at least configured with a drive test equipment API interface access tool;

[0016] The test and verification agent is configured with at least a digital twin simulation API interface access tool and a network device parameter configuration API interface access tool;

[0017] The programming engineer agent is configured with at least a knowledge graph construction API interface access tool and a training database API access tool.

[0018] Furthermore, it also includes:

[0019] The project manager agent sends assistance instructions to the programming engineer agent;

[0020] The programming engineer agent uses Python programming capabilities according to the assistance instructions to assist other agents in data statistics and analysis.

[0021] Further, establishing a group chat group on the collaboration framework;

[0022] Registering identity information of each agent in the group chat group;

[0023] Setting permissions for the group chat group so that each agent in the group chat group can receive and send messages according to the permissions;

[0024] Each agent in the group chat group integrates the corresponding API or SDK so as to be able to receive and send messages.

[0025] Furthermore, the artificial intervention agent intervenes in the group chat group, guides the discussion direction of the group chat group, and reviews the feasibility of the intermediate optimization plan.

[0026] Further, the project manager agent starts the optimization project according to the user's service request details or low-perception work order, and sends a collection instruction to the data collection agent; the data collection agent collects the data to be processed from the network device and the user device according to the collection instruction, and sends the data to be processed to the network optimization expert agent, including:

[0027] The project manager agent listens to and receives the user's service request details or low-perception work orders, and parses the request content or work order content to extract key parameters; the key parameters include optimization goals, network areas and time ranges; the project manager agent generates data collection instructions based on the parsed requests, and sends the data collection instructions to the data collection agent;

[0028] The data collection agent parses the received data collection instruction to obtain the data type and data source; the data source includes network equipment and user equipment; the data collection agent collects the data to be processed from the target network equipment and target user equipment, and preprocesses the data to be processed; the preprocessing includes format conversion, deduplication and encryption; the data collection agent sends the preprocessed data to be processed to the network optimization expert agent.

[0029] Furthermore, the network optimization expert agent performs network diagnosis on the data to be processed according to the diagnosis instruction sent by the project manager agent and the drive test data to obtain a diagnosis result; the network optimization expert agent obtains a preliminary optimization plan according to the diagnosis result, including:

[0030] The network optimization expert agent receives the diagnostic instructions, the road test data sent by the project manager agent, and the pre-processed data to be processed sent by the data collection agent;

[0031] The network optimization expert agent diagnoses the pre-processed data to be processed sent by the data collection agent according to the diagnostic instructions and the road test data to obtain a diagnostic result; the diagnostic result at least includes network bottlenecks, abnormal traffic and equipment performance; the network optimization expert agent generates a preliminary optimization plan according to the diagnostic result; the preliminary optimization plan includes adjusting parameters, upgrading equipment or optimizing routes.

[0032] Furthermore, the testing and verification agent performs performance and stability tests on the preliminary optimization solution to obtain a test report, and feeds back the test report to the network optimization expert agent, including:

[0033] The test and verification agent receives the preliminary optimization plan generated by the network optimization expert agent, and analyzes the preliminary optimization plan to obtain the analysis result; the analysis result includes the test target, test environment and test case; the test and verification agent performs the test in the specified test environment and collects the test data; generates a test report based on the test data; the test report includes the test results, performance indicators and problem analysis;

[0034] The testing and verification agent feeds back the test report to the network optimization expert agent.

[0035] Furthermore, the network optimization expert agent evaluates the test report to obtain an intermediate optimization solution, and feeds the intermediate optimization solution back to the project manager agent so that the project manager agent outputs a final optimization solution, including:

[0036] The network optimization expert agent receives the test report fed back by the test and verification agent, parses the test report, extracts key test results and performance indicators, and performs evaluation to obtain evaluation results;

[0037] The network optimization expert agent adjusts the preliminary optimization plan according to the evaluation result and generates an intermediate optimization plan; and feeds back the final optimization plan to the project manager agent.

[0038] Furthermore, the final optimization scheme includes at least one of the following:

[0039] Cover, summary, project background, optimization goals and final optimization plan; the cover includes the report title and writing date; the summary includes the optimization project background, optimization goals, main findings and recommended optimization measures; the project background includes a description of the current status of the wireless network, the source and importance of the optimization needs.

[0040] According to a second aspect of the present disclosure, an electronic device is provided. The electronic device includes: a memory and a processor, wherein a computer program is stored in the memory, and the method is implemented when the processor executes the program.

[0041] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method is implemented.

[0042] The present disclosure realizes dynamic optimization and intelligent decision-making of wireless networks by introducing a multi-agent collaboration framework, thereby improving the performance and adaptability of wireless networks. At the same time, the method has the characteristics of being distributed, self-organizing and scalable, and can effectively cope with complex and changeable wireless environments. In addition, through the construction of group chat groups, the agents can communicate and collaborate in real time, reducing the delay in information transmission. The project manager, data collection, network optimization and test and verification agents can respond and adjust the plan quickly, thereby improving the efficiency of the entire process. The data collection agent can automatically collect the pending data from network devices and user devices, ensuring that the decision-making basis for network optimization is realistic and accurate data, thereby improving the reliability of the optimization plan. The roles and responsibilities of each agent are very clear. The project manager agent is responsible for command and scheduling, the data collection agent is responsible for information collection, the network optimization expert agent is responsible for analyzing and designing the plan, and the test and verification agent is responsible for verifying the implementation effect. Such a division of labor can reduce complexity and improve the accuracy of the recommendation of wireless network optimization plans.

[0043] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein:

[0045] Figure 1 A flowchart of a method for recommending a multi-agent collaborative wireless network optimization solution according to an embodiment of the present disclosure is shown;

[0046] Figure 2 A block diagram showing the connection relationship of each multi-agent in the multi-agent collaborative wireless network optimization solution recommendation method according to an embodiment of the present disclosure is shown;

[0047] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0049] In addition, the term "and / or" in this article is only a description of the association relationship between the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0050] Figure 1 A flowchart of a method 100 for recommending a multi-agent collaborative wireless network optimization solution according to an embodiment of the present disclosure is shown. The method 100 includes:

[0051] S101, setting up several multi-agent roles on a collaborative framework that supports large model agents; the multi-agent roles include at least a project manager agent, a data collection agent, a network optimization expert agent, a manual intervention agent, a road test management agent, a test and verification agent, and a programming engineer agent; the project manager agent is used to identify optimization projects based on the user's service request details or low-perception work orders, so as to plan, coordinate and manage the entire optimization project; the data collection agent is used to collect performance data of network equipment (such as base stations, routers, switches, etc.), connection information and experience data of user equipment (such as mobile phones, tablets, etc.); it is also used to capture network configuration information and log files; the network optimization expert agent is used to generate a network optimization plan and evaluate the expected effect and cost of the network optimization plan; the manual intervention agent is used to The agent is used to receive the external input of the real network optimization expert, intervene in the dialogue to guide the discussion direction of each agent, and review and confirm the feasibility of the optimization plan; the road test management agent is used to call the road test robot and other equipment to collect road test data; the test and verification agent is used to install, debug and maintain the on-site equipment according to the network optimization plan, and realize the performance and stability test of the optimized wireless network; the programming engineer agent has Python programming ability and is familiar with graph database and relational database operations; the project manager agent and the programming engineer agent are both configured with a general large model; the data collection agent, network optimization expert agent, manual intervention agent, road test management agent and test and verification agent are all configured with a communication network large model; the communication network large model is obtained by training the general large model according to the communication industry proprietary knowledge;

[0052] S102, the project manager agent starts the optimization project according to the user's service request details or low-perception work order, and sends a collection instruction to the data collection agent;

[0053] S103, the data collection agent collects the data to be processed from the network device and the user device according to the collection instruction, and sends the data to be processed to the network optimization expert agent and the test and verification agent;

[0054] S104, the drive test management agent collects the drive test data and sends it to the network optimization expert agent;

[0055] S105, the network optimization expert agent performs network diagnosis on the data to be processed according to the diagnosis instruction sent by the project manager agent and the drive test data to obtain a diagnosis result; the network optimization expert agent obtains a preliminary optimization plan according to the diagnosis result;

[0056] S106, the testing and verification agent performs performance and stability tests on the preliminary optimization solution, obtains a test report, and feeds back the test report to the network optimization expert agent;

[0057] S107, the network optimization expert agent evaluates the test report to obtain an intermediate optimization solution, and feeds back the intermediate optimization solution to the project manager agent so that the project manager agent can output a final optimization solution.

[0058] According to the embodiments of the present invention, by introducing a multi-agent collaboration framework, dynamic optimization and intelligent decision-making of wireless networks are achieved, and the performance and adaptability of wireless networks are improved. At the same time, the method has the characteristics of being distributed, self-organizing and scalable, and can effectively cope with complex and changeable wireless environments; through the construction of group chat groups, the various agents can communicate and collaborate in real time, reducing the delay in information transmission, and the project manager, data collection, network optimization and testing and verification agents can respond and adjust the plan quickly, improving the efficiency of the entire process; the data collection agent can automatically collect the data to be processed from the network equipment and user equipment, ensuring that the decision-making basis for network optimization is realistic and accurate data, improving optimization The reliability of the solution; the roles and responsibilities of each agent are very clear. The project manager agent is responsible for command and dispatch, the data collection agent is responsible for information collection, the network optimization expert agent is responsible for analysis and design of the solution, and the test and verification agent is responsible for verifying the implementation effect. Such division of labor can reduce complexity and improve the accuracy of recommendations for wireless network optimization solutions; due to the high degree of automation, each agent can independently complete data collection, analysis and report generation, greatly reducing the need for human intervention, allowing the team to focus more on strategy and decision-making; through proactive network optimization, ensure that users' experience in the wireless network continues to improve, reduce network latency and failure rate, and improve overall customer satisfaction.

[0059] In some embodiments, Figure 2 As shown, Figure 2 A block diagram of the connection relationship of each multi-agent in the multi-agent collaborative wireless network optimization solution recommendation method according to an embodiment of the present disclosure is shown, specifically: the manual intervention agent is connected to the project manager agent, the data collection agent, the network optimization expert agent, the road test management agent, the test and verification agent and the programming engineer agent at the same time; the project manager agent is connected to the data collection agent, the network optimization expert agent, the manual intervention agent, the road test management agent, the test and verification agent and the programming engineer agent at the same time; the network optimization expert agent is connected to the road test management agent, the test and verification agent and the data collection agent at the same time; the programming engineer agent is connected to the project manager agent, the data collection agent, the network optimization expert agent, the road test management agent and the test and verification agent at the same time.

[0060] In some embodiments, the data collection agent is configured with at least a network data base API interface access tool and a user data API interface access tool; the network optimization expert agent is configured with at least a network optimization knowledge graph API access tool, a rule engine API access tool and an AI diagnosis algorithm API access tool; the road test management agent is configured with at least a road test equipment API interface access tool; the testing and verification agent is configured with at least a digital twin simulation API interface access tool and a network equipment parameter configuration API interface access tool; the programming engineer agent is configured with at least a knowledge graph construction API interface access tool and a training database API access tool.

[0061] In some embodiments, it also includes: an artificial intervention agent intervenes in the group chat group, guides the discussion direction of the group chat group, and reviews the feasibility of the intermediate optimization plan.

[0062] In some embodiments, it also includes: the project manager agent sends assistance instructions to the programming engineer agent; the programming engineer agent uses Python programming capabilities to assist other agents in data statistics and analysis based on the assistance instructions.

[0063] In some embodiments, termination conditions are set (such as the optimization suggestions have been generated, the predetermined discussion time limit has been reached, or the human intervention agent has input an "end" command). After the termination conditions are met, the project manager agent summarizes the work results of the group chat group and outputs the final optimization plan.

[0064] In some embodiments, a group chat group is established on the collaboration framework; the identity information of each agent is registered in the group chat group; permissions are set for the group chat group so that each agent in the group chat group can receive and send messages according to the permissions; each agent in the group chat group integrates a corresponding API or SDK so as to be able to receive and send messages.

[0065] According to an embodiment of the present invention, through the instant messaging function of the group chat platform, each intelligent agent is allowed to communicate in real time, ensuring the rapidity and timeliness of information transmission, thereby improving team collaboration efficiency and reducing the phenomenon of information islands; by registering the identity information of each intelligent agent, it can be ensured that the identity of each intelligent agent in the group chat is clear, preventing information from being mistransmitted and abused, and enhancing the security and reliability of the system; permission settings can ensure that each intelligent agent can only access the information it needs, preventing the leakage of confidential data, and at the same time, assigning permissions according to the needs and roles of different intelligent agents to achieve more refined management and improve the security of the workflow; compared with traditional e-mail or other communication methods, the use of the group chat platform significantly reduces communication costs, achieves more efficient communication, reduces waiting time and information transmission delays, and thus improves the accuracy of recommendations for wireless network optimization solutions.

[0066] For example, according to project needs and technical requirements, in a suitable collaborative framework that supports large model agents (such as Autogen, LangChain, Haystack, LlamaIndex, Hugging Face Create a group chat group on the collaborative framework, name it "Network Optimization Agent Collaboration Group", set the basic description information of the group chat group, and clarify its purpose and scope of work; clarify the roles and responsibilities of each agent, such as the project manager agent is responsible for overall coordination, the data collection agent is responsible for data collection, etc.; create a "robot" or "virtual user" account for each agent on the collaborative framework, and set detailed identity information according to its role, including the name, icon, introduction, etc. of the agent; perform identity authentication through system calls to the API to ensure that only authorized agents can join the group chat group; according to the responsibilities of each agent, plan its permissions in detail, such as which agents can initiate new topics and which agents can edit the group chat group settings; through the permission management function provided by the collaborative framework, configure corresponding permissions for each agent to ensure that each agent can only perform operations within its scope of responsibility; before formal use, perform permission testing to verify whether the permission settings are effective and ensure that there is no overflow or insufficient permission; according to the selected collaboration framework, select the corresponding API or SDK, such as Slack's Web API or Microsoft Teams' Bot Framework; develop an API interface for each intelligent agent so that it can receive and send messages; before actual integration, conduct a comprehensive test of the API interface to ensure that each intelligent agent can receive and send messages normally and that the message format and content meet the requirements.

[0067] In some embodiments, the project manager agent starts the optimization project according to the user's service request details or low-perception work order, and sends a collection instruction to the data collection agent; the data collection agent collects the data to be processed from the network equipment and the user equipment according to the collection instruction, and sends the data to be processed to the network optimization expert agent, including: the project manager agent listens to and receives the user's service request details or low-perception work order, and parses the request content or the work order content to extract key parameters; the key parameters include optimization goals, network areas and time ranges; the project manager agent generates data collection instructions according to the parsed request, and sends the data collection instructions to the data collection agent; the data collection agent parses the received data collection instructions to obtain the data type and data source; the data source includes network equipment and user equipment; the data collection agent collects the data to be processed from the target network equipment and the target user equipment, and pre-processes the data to be processed; the pre-processing includes format conversion, deduplication and encryption; the data collection agent sends the pre-processed data to the network optimization expert agent.

[0068] According to an embodiment of the present invention, the project manager agent automatically monitors and receives the user's optimization request, thereby reducing manual intervention and improving the speed and efficiency of request processing; by extracting key parameters (such as optimization goals, network areas and time ranges), the scope and content of data collection can be effectively narrowed, the collection of invalid data can be avoided, and the pertinence of subsequent analysis can be improved; the project manager agent generates specific data collection instructions based on the parsed requests, and this flexibility can quickly respond to different user needs and adapt to diverse optimization scenarios; the data collection agent parses the received data collection instructions, and can clarify the data type and data source, ensuring that the data collection process is fast and efficient, and reducing errors in understanding and information loss; through fast and efficient data collection and preprocessing, the network optimization expert agent can obtain the required data more quickly, analyze and propose optimization plans, which speeds up the response time of the entire optimization process, thereby improving the accuracy of the recommendation of wireless network optimization plans.

[0069] In some embodiments, the network optimization expert agent performs network diagnosis on the data to be processed according to the diagnostic instructions sent by the project manager agent and the road test data to obtain a diagnostic result; the network optimization expert agent obtains a preliminary optimization plan according to the diagnostic result, including: the network optimization expert agent receives the diagnostic instructions sent by the project manager agent, the road test data and the pre-processed data to be processed sent by the data collection agent; the network optimization expert agent diagnoses the pre-processed data to be processed sent by the data collection agent according to the diagnostic instructions and the road test data to obtain a diagnostic result; the diagnostic result includes at least network bottlenecks, abnormal traffic and equipment performance; the network optimization expert agent generates a preliminary optimization plan according to the diagnostic result; the preliminary optimization plan includes adjusting parameters, upgrading equipment or optimizing routes.

[0070] According to the embodiment of the present invention, the network optimization expert intelligent agent automatically generates a preliminary optimization plan based on the diagnosis results, which reduces manual intervention and improves the efficiency and speed of plan generation. This automation can quickly respond to network optimization needs and reduce reaction time; the preliminary optimization plan includes a variety of optimization measures, such as adjusting parameters, upgrading equipment or optimizing routes. This multi-dimensional strategy provides a flexible solution that can comprehensively deal with different types of network problems and improve the overall optimization effect; through a fast and accurate diagnosis process and a real-time generated optimization plan, it can quickly solve the problems encountered by users, improve the user's network experience, and thus improve user satisfaction. .

[0071] For example, first ensure that the communication mechanism between the project manager agent, the data collection agent and the network optimization expert agent can achieve real-time communication through an integrated API or message queue; the network optimization expert agent receives the diagnostic instructions sent by the project manager agent, including specific diagnostic goals, data ranges and requirements, etc.; ensure that the data collection agent can send pre-processed data (such as traffic data, equipment performance indicators, etc.) directly to the network optimization expert agent; verify the integrity and validity of the received data to be processed, and ensure that the data is not lost or damaged. If a problem is found, the network optimization expert agent needs to request the data collection agent to resend the data; according to the preset diagnostic instructions, select a suitable diagnostic model or algorithm to analyze the data to be processed, for example, statistical analysis methods, machine learning models or network traffic analysis tools can be used; generate diagnostic results based on the analysis results, specifically including: identifying problems such as traffic peaks, insufficient bandwidth, delay causes, etc., and detecting The diagnostic results are used to evaluate the current network status, analyze the impact of the diagnostic results on the overall network performance item by item, and propose corresponding optimization measures; the preliminary optimization plan should include the following three parts and corresponding adjustment suggestions: According to the diagnostic results, adjust the parameter settings of routers and switches, such as bandwidth control, QoS (quality of service) level settings, etc.; if it is found that some equipment has insufficient performance, record the equipment that needs to be replaced or upgraded, and recommend the purchase of corresponding new equipment; analyze the current routing strategy and propose an optimized routing plan, which may involve reconfiguring routing protocols or adjusting priorities; organize the diagnostic results and preliminary optimization plan into a detailed document, including steps, analysis methods, results and suggestions; feedback the preliminary optimization plan to the project manager agent through an integrated communication mechanism to ensure that it is informed of the diagnosis and optimization progress in a timely manner.

[0072] In some embodiments, the test and verification agent performs performance and stability tests on the preliminary optimization plan, obtains a test report, and feeds back the test report to the network optimization expert agent, including: the test and verification agent receives the preliminary optimization plan generated by the network optimization expert agent, and parses the preliminary optimization plan to obtain a parsing result; the parsing result includes a test objective, a test environment, and a test case; the test and verification agent performs a test in a specified test environment and collects test data; a test report is generated based on the test data; the test report includes test results, performance indicators, and problem analysis; the test and verification agent feeds back the test report to the network optimization expert agent.

[0073] According to an embodiment of the present invention, after analyzing the preliminary optimization plan, the test and verification agent can clearly define the test objectives, ensure that the test work is highly targeted and has a clear direction, and help verify the effectiveness and reliability of the optimization plan; by feeding back the test results to the network optimization expert agent, a closed-loop optimization feedback mechanism is formed, so that the optimization decision can be based on real test data, thereby improving the scientificity and effectiveness of the decision; by effectively verifying and optimizing the network plan, the end-user experience can be greatly improved.

[0074] For example, ensure that the test and verification agent can establish a stable communication channel with the network optimization expert agent, usually using an API or message queue mechanism; the test and verification agent obtains all relevant information of the preliminary optimization plan, including parameter adjustment, equipment upgrade and specific content of route optimization; the test and verification agent parses the obtained optimization plan and extracts key information, including: clarifying the purpose of this test, such as verifying network performance improvement, identifying potential problems, etc., determining the network environment configuration that needs to be tested, including network topology, equipment configuration, data traffic type, etc., generating corresponding test cases based on the optimization plan, covering normal conditions, boundary conditions and abnormal conditions, to ensure comprehensive testing of optimization effects; configuring the test environment according to the parsed test environment requirements to ensure that it is as consistent as possible with the actual operating environment; deploying necessary hardware and software, and installing monitoring tools and data collection components; the test and verification agent executes the generated test cases in the specified test environment Run the test; record the running results of each test case, including the success and failure status, running time, resource consumption, etc.; collect network performance data in real time during the execution process, including but not limited to: throughput, delay, packet loss rate, device CPU and memory usage; determine the structure of the test report and standardize the test report format, including the following modules: list the execution results of each case, summarize the overall execution status (pass, fail, etc.), record the specific values ​​of each performance indicator in detail, compare and analyze with the optimization goals, conduct in-depth analysis of the problems found during the test, record the description of abnormal situations and cause analysis, and put forward corresponding improvement suggestions; the test and verification agent feeds back the test report to the network optimization expert agent through the communication mechanism to ensure that it is received in time and conducts subsequent analysis; if serious problems or deviations are found in the test report, the test and verification agent can actively initiate a discussion with the network optimization expert agent in order to quickly adjust the optimization plan.

[0075] In some embodiments, the network optimization expert agent evaluates the test report to obtain an intermediate optimization plan, and feeds back the intermediate optimization plan to the project manager agent so that the project manager agent can output a final optimization plan, including: the network optimization expert agent receives the test report fed back by the test and verification agent, parses the test report, extracts key test results and performance indicators, and evaluates to obtain an evaluation result; the network optimization expert agent adjusts the preliminary optimization plan based on the evaluation result to generate an intermediate optimization plan; and feeds back the final optimization plan to the project manager agent.

[0076] In some embodiments, the wireless network optimization report may include: a cover (such as report title, writing date), a summary (such as optimization project background, optimization goals, main findings, and recommended optimization measures), a project background (such as a description of the current state of the wireless network, the source and importance of optimization needs), optimization goals and a final optimization plan (such as optimization measures proposed for the problems found, implementation steps and processes, and the expected implementation effects of each measure), and an appendix (such as additional data charts, references and materials, and related codes and algorithm descriptions).

[0077] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0078] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0079] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0080] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0081] The electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in a ROM 302 or a computer program loaded from a storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An I / O interface 305 is also connected to the bus 304.

[0082] A number of components in the electronic device 300 are connected to the I / O interface 305, including: an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0083] The computing unit 301 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 301 performs the various methods and processes described above, such as a multi-agent collaborative wireless network optimization solution recommendation method. For example, in some embodiments, the multi-agent collaborative wireless network optimization solution recommendation method may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 308. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded into the RAM 303 and executed by the computing unit 301, one or more steps of the multi-agent collaborative wireless network optimization solution recommendation method described above may be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the multi-agent collaborative wireless network optimization solution recommendation method in any other appropriate manner (eg, by means of firmware).

[0084] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0085] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0086] In the context of the present disclosure, a readable storage medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A readable storage medium may be a machine-readable signal medium or a machine-readable storage medium. A readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of readable storage media may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0087] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0088] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0089] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0090] It should be understood that the above-mentioned various forms of processes can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solution of this disclosure can be achieved, and this document is not limited here.

[0091] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for recommending a multi-agent collaborative wireless network optimization solution, characterized in that: The invention comprises setting a plurality of multi-agent roles on a collaborative framework supporting large model agents; wherein, setting a plurality of multi-agent roles on a collaborative framework supporting large model agents comprises: establishing a group chat group on the collaborative framework; registering the identity information of each agent in the group chat group; setting permissions for the group chat group so that each agent in the group chat group can receive and send messages according to the permissions; each agent in the group chat group integrates a corresponding API or SDK so as to be able to receive and send messages; the multi-agent roles at least include a project manager agent, a data collection agent, a network optimization expert agent, a manual intervention agent, a road test management agent, a test and verification agent, and a programming engineer agent; the project manager agent and the programming engineer agent are both configured with a general large model; the data collection agent, the network optimization expert agent, the manual intervention agent, the road test management agent, and the test and verification agent are all configured with a communication network large model; the communication network large model is obtained by training the general large model according to the communication industry proprietary knowledge; the programming engineer agent has Python programming ability and is familiar with graph database and relational database operations; The project manager agent starts the optimization project based on the user's service request details or low-perception work orders, and sends collection instructions to the data collection agent; The data collection agent collects the data to be processed from the network equipment and the user equipment according to the collection instruction, and sends the data to be processed to the network optimization expert agent and the test and verification agent; The drive test management agent collects the drive test data and sends it to the network optimization expert agent; The network optimization expert agent performs network diagnosis on the data to be processed according to the diagnosis instruction sent by the project manager agent and the road test data to obtain a diagnosis result; the network optimization expert agent obtains a preliminary optimization plan according to the diagnosis result; The testing and verification agent performs performance and stability tests on the preliminary optimization scheme, obtains a test report, and feeds back the test report to the network optimization expert agent; The network optimization expert agent evaluates the test report to obtain an intermediate optimization solution, and feeds the intermediate optimization solution back to the project manager agent so that the project manager agent can output a final optimization solution; The artificial intervention agent intervenes in the group chat group, guides the discussion direction of the group chat group, and reviews the feasibility of the intermediate optimization plan.

2. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: The data collection agent is at least configured with a network data base API interface access tool and a user data API interface access tool; The network optimization expert agent is configured with at least a network optimization knowledge graph API access tool, a rule engine API access tool, and an AI diagnosis algorithm API access tool; The drive test management agent is at least configured with a drive test equipment API interface access tool; The test and verification agent is configured with at least a digital twin simulation API interface access tool and a network device parameter configuration API interface access tool; The programming engineer agent is configured with at least a knowledge graph construction API interface access tool and a training database API access tool.

3. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: Also includes: The project manager agent sends assistance instructions to the programming engineer agent; The programming engineer agent uses Python programming capabilities according to the assistance instructions to assist other agents in data statistics and analysis.

4. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: The project manager agent starts the optimization project according to the user's service request details or low-perception work order, and sends a collection instruction to the data collection agent; The data collection agent collects the data to be processed from the network device and the user device according to the collection instruction, and sends the data to be processed to the network optimization expert agent, including: The project manager agent listens to and receives the user's service request details or low-perception work orders, and parses the request content or work order content to extract key parameters; the key parameters include optimization goals, network areas and time ranges; the project manager agent generates data collection instructions based on the parsed requests, and sends the data collection instructions to the data collection agent; The data collection agent parses the received data collection instruction to obtain the data type and data source; the data source includes network equipment and user equipment; the data collection agent collects the data to be processed from the target network equipment and target user equipment, and preprocesses the data to be processed; the preprocessing includes format conversion, deduplication and encryption; the data collection agent sends the preprocessed data to be processed to the network optimization expert agent.

5. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: The network optimization expert agent performs network diagnosis on the data to be processed according to the diagnosis instruction sent by the project manager agent and the drive test data to obtain a diagnosis result; The network optimization expert agent obtains a preliminary optimization plan based on the diagnosis results, including: The network optimization expert agent receives the diagnostic instructions, the road test data sent by the project manager agent, and the pre-processed data to be processed sent by the data collection agent; The network optimization expert agent diagnoses the pre-processed data to be processed sent by the data collection agent according to the diagnostic instructions and the road test data to obtain a diagnostic result; the diagnostic result at least includes network bottlenecks, abnormal traffic and equipment performance; the network optimization expert agent generates a preliminary optimization plan according to the diagnostic result; the preliminary optimization plan includes adjusting parameters, upgrading equipment or optimizing routes.

6. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: The testing and verification agent performs performance and stability tests on the preliminary optimization scheme, obtains a test report, and feeds back the test report to the network optimization expert agent, including: The test and verification agent receives the preliminary optimization plan generated by the network optimization expert agent, and analyzes the preliminary optimization plan to obtain the analysis result; the analysis result includes the test target, test environment and test case; the test and verification agent performs the test in the specified test environment and collects the test data; generates a test report based on the test data; the test report includes the test results, performance indicators and problem analysis; The testing and verification agent feeds back the test report to the network optimization expert agent.

7. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 1, characterized in that: The network optimization expert agent evaluates the test report to obtain an intermediate optimization solution, and feeds the intermediate optimization solution back to the project manager agent so that the project manager agent outputs a final optimization solution, including: The network optimization expert agent receives the test report fed back by the test and verification agent, parses the test report, extracts key test results and performance indicators, and performs evaluation to obtain evaluation results; The network optimization expert agent adjusts the preliminary optimization plan according to the evaluation result and generates an intermediate optimization plan; and feeds back the final optimization plan to the project manager agent.

8. The method for recommending a multi-agent collaborative wireless network optimization solution according to claim 7, characterized in that: The final optimization solution includes at least one of the following: Cover, summary, project background, optimization goals and final optimization plan; the cover includes the report title and writing date; the summary includes the optimization project background, optimization goals, main findings and recommended optimization measures; the project background includes a description of the current status of the wireless network, the source and importance of the optimization needs.

Images