A container cloud intelligent console implementation method, system, device and storage medium

Abstract

The application discloses a container cloud intelligent console implementation method, system and device and a storage medium, belongs to the field of Internet technology cloud native technology, and solves the technical problem of limitations of a large language model in application to Kubernetes operation and maintenance. The method is: selecting an LLM pre-training large model; establishing a Kubernetes knowledge base through a data collector; retraining the LLM pre-training model by using a large model instruction data set; parameter fine-tuning the LLM pre-training model; deploying the LLM large model service, AI middle platform service involving large model interaction and intelligent container cloud management console system in a Kubernetes cluster; providing the following seven intelligent functions according to the output of the LLM pre-training model; performing production environment feedback and data backflow; updating the knowledge base according to the feedback and data backflow, retraining the LLM pre-training model; and redeploying the retrained LLM pre-training model. The operation and maintenance can be more efficient, accurate and intelligent.

Description

TECHNICAL FIELD

[0001] The application relates to the field of Internet technology cloud native technology, in particular to a container cloud intelligent console implementation method, system, device and storage medium. BACKGROUND

[0002] In today's rapidly developing information technology, cloud computing has become a core component of enterprise IT structure. It provides flexible and scalable IT resources through the network, enabling enterprises to quickly adjust computing, storage and network resources according to demand. The development of cloud computing has given birth to a series of new technologies, among which container technology is particularly prominent. Containers are a lightweight virtualization form that allows applications and their dependencies to be packaged together for quick deployment and operation in any environment. Due to its efficient resource utilization and portability, container technology has quickly gained the favor of developers and enterprises.

[0003] Among the many container orchestration tools, Kubernetes (K8s) as an open source project has become an industry standard. Kubernetes provides powerful functions to automate the deployment, scaling and management of containers, enabling applications to run flexibly and efficiently in various cloud environments. With the popularity of microservices architecture, more and more enterprises have begun to use Kubernetes to improve the maintainability and flexibility of applications. However, the complexity of Kubernetes also brings new challenges to developers and operations personnel (DevOps).

[0004] Behind the flexibility and powerful functions of Kubernetes, there is hidden complexity in management and operation. The following are some major challenges:

[0005] Complex configuration management: Kubernetes relies on YAML files for configuration and resource management. Any errors in the YAML file can cause service interruption or failure, and ensuring the accuracy and consistency of the configuration file is a difficult task.

[0006] Difficult troubleshooting: In a distributed system, faults can be caused by a variety of reasons, including network problems, resource shortages, configuration errors, etc. Operations personnel need to have rich experience and knowledge to quickly locate problems and develop solutions.

[0007] Insufficient resource optimization: As the size of the application increases, how to reasonably allocate, manage and optimize cluster resources to improve performance and reduce costs is a problem that needs to be solved.

[0008] Constantly changing technology stack: The Kubernetes ecosystem changes rapidly, with new tools and technologies emerging constantly, and operations personnel need to continuously learn and master new knowledge to keep up with the pace of technology.

[0009] Complex operation flow: Traditional DevOps processes often suffer from tool chain fragmentation, lack of a global perspective, and optimized decision support systems, making continuous integration and continuous deployment (CI / CD) processes inefficient and prone to errors.

[0010] In recent years, natural language processing (NLP) technology based on deep learning has made breakthroughs, especially the emergence of large language models (LLM), opening up a new chapter in artificial intelligence. Models such as OpenAI's GPT series, Google's BERT, etc., have shown super-strong capabilities in language understanding and generation. These models can learn the structure, semantics, and context relationships of language by training a large amount of text data, and then generate fluent text, perform language translation, answer questions, and engage in conversations.

[0011] These large language models provide new ideas for solving complex cognitive tasks. For example, through natural language interaction with computers, users can complete tasks in a more intuitive and easy way without deep understanding of underlying technical details. This intelligent technical solution has achieved remarkable success in many fields, and some companies have even begun to apply it to automated customer service, content generation, code review, and other scenarios.

[0012] Combining large language models with Kubernetes operations can provide great help to operations personnel:

[0013] 1. Intelligent troubleshooting: Large language models can analyze error logs, system status, and historical data, quickly present potential problems and solutions to operations personnel, and shorten fault handling time.

[0014] 2. Automated configuration recommendation: Through natural language processing, large language models can automatically generate or recommend configuration files based on user needs, reducing the complexity of manual operations and avoiding human errors.

[0015] 3. Dynamic learning and adaptation: Combined with machine learning and user feedback, the system can continuously update the knowledge base to adapt to new operational scenarios and technical changes, enhancing system flexibility.

[0016] 4. Optimized decision support: Using the reasoning capabilities of large language models, it can provide data-driven recommendations for complex decisions such as resource allocation and architecture optimization, improving operational efficiency.

[0017] 5. User-friendly interface: Through natural language interaction with users, it reduces the barrier between users and technology, allowing people without deep technical backgrounds to effectively manage Kubernetes clusters.

[0018] Although large language models have shown their potential in many fields, there are still some limitations when applied to Kubernetes operations. For example:

[0019] Insufficient knowledge depth: Although large language models can generate natural language text, they may not fully grasp the deep knowledge in the Kubernetes field, especially when dealing with specific technical problems.

[0020] Model adaptability: Since large language models are mainly based on general corpus, when applied to specific fields, they may need to be retrained to improve their performance on specific tasks.

[0021] Data privacy and security: When dealing with enterprise sensitive information, how to ensure data privacy and security is still an important challenge. How to protect users' data from being misused when interacting with AI systems will be a major consideration in design. SUMMARY

[0022] The technical problem to be solved by the present application is to overcome the above-mentioned deficiencies of the prior art. The first object of the present application is to provide a container cloud intelligent console implementation method, which can combine large language models with container cloud management, and realize end-to-end operation automation through an intelligent console, making operation more efficient, accurate and intelligent.

[0023] The second object of the present application is to provide a container cloud intelligent console implementation system.

[0024] The third object of the present application is to provide a computer device.

[0025] The fourth object of the present application is to provide a computer storage medium.

[0026] In order to achieve the above-mentioned first object, the present application provides a container cloud intelligent console implementation method, comprising the following steps:

[0027] Step S1. Select the type of LLM large model to access; access different LLM large models by adapting multiple LLM large model interfaces, including open source general large models and industry large models on the network; after determining the LLM pre-training large model to be used, modify the corresponding configuration file to complete the access of the LLM large model;

[0028] Step S2. Establish a Kubernetes knowledge base through a data collector; the data collector will automatically collect large model instruction data sets in the Kubernetes cluster, and also collect user-initiated knowledge data; the data collector integrates the large model instruction data sets and the user-initiated knowledge data to form a knowledge base;

[0029] Step S3. Based on the LLM pre-training model, the LLM pre-training model is retrained using the large model instruction data set to enhance the LLM pre-training model's mastery, reasoning and generation ability of Kubernetes knowledge;

[0030] Step S4. Parameter fine-tuning is performed on the retrained LLM pre-training model to improve the generality and correctness of the solutions provided by the LLM pre-training model;

[0031] Step S5. The fine-tuned LLM pre-training model LLM large model service, AI middle platform service involving large model interaction and intelligent container cloud management console system are deployed in the Kubernetes cluster;

[0032] Step S6. The intelligent container cloud management console system interacts with the fine-tuned LLM pre-training model through the AI middle platform service, and provides the following seven intelligent functions according to the output of the LLM pre-training model: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestion, network topology optimization suggestion, pipeline compilation error analysis, alarm analysis and processing method;

[0033] Step S7. Production environment feedback and data backflow are performed;

[0034] Step S8. After automatic screening or manual screening by the intelligent container cloud management console system, the backflow data is added to the knowledge base;

[0035] Step S9. The knowledge base is updated according to the feedback and data backflow, and the LLM pre-training model is retrained according to the updated knowledge base;

[0036] Step S10. The LLM large model service of the retrained LLM pre-training model is redeployed, and the model performance is continuously iteratively optimized.

[0037] As a further improvement, in step S2, the large model instruction data set focuses on Kubernetes operation and maintenance, and is a specific solution covering various Kubernetes problems, including Kubernetes official guidance, all YAML data of the current cluster, ETCD data, Kubernetes exception analysis and solutions on the Internet, and error analysis and solutions for compilation and construction.

[0038] Further, in step S2, user uploaded document data and user added custom knowledge data to the knowledge base are obtained; the document data includes word files, pdf files and directly uploaded text data; the word files and pdf files are parsed into text and included in the knowledge base together with the directly uploaded text data.

[0039] Furthermore, in step S6, the system first selects the question that needs to be submitted by the intelligent container cloud management console system to request the LLM pre-trained model, determines the category to which the question belongs, and then submits it to the corresponding large model Agent to process the intelligent function of the corresponding category.

[0040] Furthermore, in step S6, the seven intelligent functions are specifically as follows:

[0041] Intelligent configuration recommendation: When creating Kubernetes resources using the wizard mode, the intelligent container cloud management console system automatically fills in some input boxes and highlights and recommends the options that need to be enabled or selected, which can reduce the scenarios where users need to frequently copy and paste and the selection of almost repetitive items;

[0042] Intelligent YAML Completion: When writing YAML files for Kubernetes to define Kubernetes resource objects, the intelligent container cloud management console system will automatically complete the YAML at the current cursor position. You can use a shortcut key to apply the YAML fragments added by intelligent YAML completion.

[0043] Kubernetes Error Analysis: On the error events in the container cloud console, an intelligent analysis function can be triggered. The intelligent container cloud management console system will combine the current cluster content, official documentation, and solutions on the Internet to describe in detail the possible causes of the error and the corresponding solutions.

[0044] Container application deployment optimization suggestions: Intelligent optimization suggestions can be provided for deployed applications to improve performance and resource utilization, making containerized application deployment more intelligent and efficient, and improving resource utilization and performance. Intelligent optimization suggestions include: adjusting the number of deployments, adding health checks, node affinity suggestions, node anti-affinity suggestions, and pod affinity suggestions.

[0045] Network topology optimization suggestions: Optimization suggestions can be provided for service discovery methods, allowing you to select optimization strategies suitable for the current architecture and business needs, effectively manage resources, and reduce operation and maintenance costs; optimization suggestions include: service types and adjustments to Pod distribution schemes;

[0046] Pipeline Compilation Error Analysis: When a compilation error occurs during pipeline execution, the intelligent container cloud management console system generates a corresponding error log. The error log records the specific location of the error, the error code, and related context information. Through the pipeline compilation error analysis function, the root cause of the compilation error can be accurately determined by analyzing the error log. Root causes include syntax problems, missing dependencies, and configuration errors. For each type of error, the intelligent container cloud management console system provides specific solutions, including code modification, dependency updates, and configuration adjustments.

[0047] Alarm Analysis: The alarm analysis function can analyze historical alarm data to discover potential problem patterns and trends; and provide regularly generated alarm reports that summarize alarm events and their solutions in a recent period.

[0048] Furthermore, in step S7, feedback and data return include two forms:

[0049] The first form is: when actively selecting recommended configuration items and using YAML completion, automatically submit the adoption status to the AI ​​middleware service to mark the data as approved;

[0050] The second format is as follows: After the LLM pre-trained model submits analysis and provides suggestions, the intelligent container cloud management console system will provide an option below the response to agree or disagree with the large model's suggestions. Users can choose based on whether the analysis is correct and whether the suggestions are reasonable and effective, thereby submitting data to the AI ​​platform service. In addition, users can also upload their own answers for data feedback.

[0051] To achieve the second objective mentioned above, this invention provides a container cloud intelligent console implementation system, comprising:

[0052] The selection module is used to choose the type of LLM large model to be accessed; by adapting to various LLM large model interfaces, different LLM large models can be accessed, including open-source general large models on the Internet and industry large models; after determining the LLM pre-trained large model to be used, the access of the LLM large model can be completed by modifying the corresponding configuration file.

[0053] The knowledge base module is used to build a Kubernetes knowledge base through the data collector. The data collector automatically collects large model instruction datasets in the Kubernetes cluster, and also collects knowledge data actively uploaded by users. The data collector integrates the large model instruction datasets and the knowledge data actively uploaded by users to form the knowledge base.

[0054] The training module is used to retrain the LLM pre-trained model using the large model instruction dataset, thereby enhancing the LLM pre-trained model's mastery, reasoning, and generation capabilities of Kubernetes knowledge; and to fine-tune the parameters of the retrained LLM pre-trained model to improve the versatility and correctness of the solutions provided by the LLM pre-trained model.

[0055] The deployment module is used to deploy the finely tuned LLM pre-trained model's LLM large model service, the AI ​​middleware service involving large model interaction, and the intelligent container cloud management console system on the Kubernetes cluster;

[0056] The intelligent function module is used to enable the intelligent container cloud management console system to interact with the fine-tuned LLM pre-trained model through the AI ​​middleware service, and provide the following 7 intelligent functions based on the output of the LLM pre-trained model: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestions, network topology optimization suggestions, pipeline compilation error analysis, alarm analysis and providing processing methods;

[0057] The feedback module is used for production environment feedback and data return; after being automatically or manually filtered by the intelligent container cloud management console system, the returned data is added to the knowledge base.

[0058] The update module is used to update the knowledge base based on feedback and data feedback. The LLM pre-trained model is retrained based on the updated knowledge base. The LLM large model service of the retrained LLM pre-trained model is redeployed to continuously iterate and optimize the model performance.

[0059] To achieve the third objective mentioned above, the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned container cloud intelligent console implementation method.

[0060] To achieve the fourth objective mentioned above, the present invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described container cloud intelligent console implementation method.

[0061] Beneficial effects

[0062] Compared with the prior art, the advantages of this invention are as follows:

[0063] 1. This invention, through automated operation and maintenance processes and intelligent fault diagnosis, significantly reduces the working time of operation and maintenance personnel, enabling teams to resolve problems more quickly and thus improving overall work efficiency. Utilizing the analytical capabilities of large language models and intelligent recommendation functions, the incidence of human error can be reduced, the accuracy of configuration and operation can be enhanced, and the stability and reliability of the system can be ensured. Introducing intelligent monitoring and early warning mechanisms into operation and maintenance management can promptly identify potential security risks and reduce the risk of data leakage and system failure through rapid response.

[0064] 2. This invention supports intelligent decision-making. Through self-learning and cyclical feedback mechanisms, the console can continuously adjust itself according to changing environments, providing data-driven intelligent decision support and helping the operations and maintenance team make more targeted optimizations and adjustments. Based on intelligent tracking of resource usage, the system dynamically adjusts resource allocation to maximize resource utilization efficiency and reduce waste of idle resources. This optimization directly leads to cost reduction, enabling enterprises to effectively control operational costs and improve overall business responsiveness and market competitiveness.

[0065] 3. This invention offers a user-friendly experience, allowing users to interact with the console through natural language, lowering the technical barrier and enabling non-technical personnel to operate it smoothly, thus broadening its scope of application.

[0066] 4. This invention improves the operational efficiency of Kubernetes by constructing an intelligent container cloud management solution, making operations more efficient, accurate, and intelligent. Attached Figure Description

[0067] Fig. 1 This is a flowchart of the present invention;

[0068] Fig. 2 A summary diagram of the functions provided by the intelligent container cloud management console. Detailed Implementation

[0069] The present invention will be further described below with reference to specific embodiments shown in the accompanying drawings.

[0070] See Figs. 1-2 A method for implementing a container cloud intelligent console includes the following steps S1 to S10:

[0071] Step S1. Select the type of LLM model to access; by adapting to various LLM model interfaces, different LLM models can be accessed. These include open-source general-purpose models and industry-specific models. After determining the LLM pre-trained model to use, modify the corresponding configuration file to complete the LLM model access. As a core component of the system, the LLM model is responsible for processing and analyzing complex data and instructions.

[0072] By adapting to different large language model interfaces, multiple models can be accessed, providing users with flexible choices and ensuring that the system can be adjusted according to specific needs.

[0073] Step S2. Establish a Kubernetes knowledge base using the data collector. The data collector automatically collects large model instruction datasets within the Kubernetes cluster, and also collects knowledge data actively uploaded by users. The data collector integrates the large model instruction datasets and user-uploaded knowledge data to form a knowledge base. The data collector is used to collect and integrate multi-source data, including but not limited to: collecting official Kubernetes guidelines, all YAML data in the current cluster, ETCD data, Kubernetes anomaly analysis and solutions from the internet, compilation and build error analysis and solutions, and user-uploaded knowledge data. This data will be integrated to build a knowledge base for system analysis and decision-making.

[0074] Furthermore, the large model instruction dataset focuses on Kubernetes operations and maintenance, and provides specific solutions to various Kubernetes issues, including official Kubernetes guidance, all YAML data of the current cluster, ETCD data, Kubernetes anomaly analysis and solutions from the Internet, and error analysis and solutions for compilation and build.

[0075] Furthermore, it acquires user-uploaded document data and user-added custom knowledge data to the knowledge base; document data includes Word files, PDF files, and directly uploaded text data; Word files and PDF files are parsed into text and included in the knowledge base along with the directly uploaded text data.

[0076] By implementing data collection and building a rich knowledge base, including user-defined data, we can ensure that the model has targeted learning and reasoning capabilities.

[0077] Step S3. Based on the LLM pre-trained model, the LLM pre-trained model is retrained using a large model instruction dataset to enhance the LLM pre-trained model's ability to master, reason about, and generate Kubernetes knowledge.

[0078] Step S4. Fine-tune the parameters of the retrained LLM pre-trained model to improve the versatility and correctness of the solution provided by the LLM pre-trained model.

[0079] By leveraging user feedback, dynamic knowledge iteration and model retraining are achieved, ensuring the system's usability and accuracy.

[0080] Step S5. Deploy the finely tuned LLM pre-trained model's LLM large model service, the AI ​​middleware service involving large model interaction, and the intelligent container cloud management console system in the Kubernetes cluster.

[0081] AI Platform Service: Responsible for interacting with large language models, generating and filtering feedback data to optimize the system's decision-making process. Intelligent Container Cloud Management Console System provides the user interface, interacts with users, and offers intelligent container cloud platform solutions to help users efficiently manage and maintain the container cloud platform.

[0082] Step S6. The intelligent container cloud management console system interacts with the fine-tuned LLM pre-trained model through the AI ​​middleware service, and provides the following 7 intelligent functions based on the output of the LLM pre-trained model: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestions, network topology optimization suggestions, pipeline compilation error analysis, alarm analysis and providing handling methods.

[0083] Furthermore, the system first selects the issue to be submitted to the intelligent container cloud management console system to request the LLM pre-trained model, determines the category of the issue, and then submits it to the corresponding large model agent to process the intelligent functions of the corresponding category.

[0084] The seven intelligent functions are as follows:

[0085] Intelligent configuration recommendations: When creating Kubernetes resources using the wizard mode, the intelligent container cloud management console system automatically fills in some input boxes and highlights recommended options that need to be enabled or selected, which can reduce the scenarios where users need to frequently copy and paste and the selection of nearly repetitive items.

[0086] Intelligent YAML Completion: When writing YAML files for Kubernetes to define Kubernetes resource objects, the intelligent container cloud management console system will automatically complete the YAML at the current cursor position. You can then apply the YAML fragments added by intelligent YAML completion using a keyboard shortcut.

[0087] Kubernetes Error Analysis: The intelligent analysis function can be triggered on the error events in the container cloud console. The intelligent container cloud management console system will combine the current cluster content, official documentation, and solutions on the Internet to describe in detail the possible causes of the error and the corresponding solutions.

[0088] Container application deployment optimization suggestions: It can provide intelligent optimization suggestions for deployed applications, which can improve performance and resource utilization, making containerized application deployment more intelligent and efficient, and improving resource utilization and performance. Intelligent optimization suggestions include: adjusting the number of deployments, adding health checks, node affinity suggestions, node anti-affinity suggestions, and pod affinity suggestions.

[0089] Network topology optimization suggestions: Optimization suggestions can be provided for service discovery methods, allowing you to select optimization strategies that suit the current architecture and business needs, effectively manage resources and reduce operation and maintenance costs; optimization suggestions include: service types and adjusting Pod distribution schemes.

[0090] Pipeline Compilation Error Analysis: When a compilation error occurs during pipeline execution, the intelligent container cloud management console system generates a corresponding error log. The error log records the specific location of the error, the error code, and related context information. Through the pipeline compilation error analysis function, the root cause of the compilation error can be accurately determined by analyzing the error log. Root causes include syntax problems, missing dependencies, and configuration errors. For each type of error, the intelligent container cloud management console system provides specific solutions. These solutions include modifying code, updating dependencies, and adjusting configuration settings.

[0091] Alarm Analysis: The alarm analysis function can analyze historical alarm data to identify potential problem patterns and trends. It also provides regularly generated alarm reports that summarize recent alarm events and their solutions.

[0092] Intelligent decision support provides a variety of intelligent functions, including configuration recommendation, fault analysis, and resource optimization, to enhance the work efficiency of operation and maintenance personnel.

[0093] Step S7. Perform production environment feedback and data feedback. Feedback and data feedback include two forms:

[0094] The first approach involves automatically submitting the adoption status to the AI ​​platform service to mark the data as approved when actively selecting recommended configuration items and using YAML autocomplete.

[0095] The second approach involves submitting an analysis and providing suggestions for the LLM pre-trained model. The intelligent container cloud management console will then offer an option below the response to agree with or disagree with the model's suggestions. Users can choose based on the accuracy of the analysis and the reasonableness and effectiveness of the suggestions, thus submitting data to the AI ​​platform service. Additionally, users can upload their own responses for data feedback.

[0096] Step S8. After automatic or manual filtering by the intelligent container cloud management console system, the returned data is added to the knowledge base.

[0097] Step S9. Update the knowledge base based on feedback and data feedback, and retrain the LLM pre-trained model based on the updated knowledge base.

[0098] Step S10. Redeploy the retrained LLM pre-trained model to the LLM large model service and continuously iterate and optimize the model performance. The self-learning and feedback mechanism enables the console to continuously adjust itself according to the changing environment, providing data-driven intelligent decision support and helping the operations team make more targeted optimizations and adjustments.

[0099] A container cloud intelligent console implementation system includes:

[0100] The selection module is used to choose the type of LLM large model to be accessed; by adapting to various LLM large model interfaces, different LLM large models can be accessed, including open-source general large models on the Internet and industry large models; after determining the LLM pre-trained large model to be used, the access of the LLM large model can be completed by modifying the corresponding configuration file.

[0101] The knowledge base module is used to build a Kubernetes knowledge base through the data collector. The data collector automatically collects large model instruction datasets in the Kubernetes cluster, and also collects knowledge data actively uploaded by users. The data collector integrates the large model instruction datasets and the knowledge data actively uploaded by users to form the knowledge base.

[0102] The training module is used to retrain the LLM pre-trained model using a large model instruction dataset, thereby enhancing the LLM pre-trained model's mastery, reasoning, and generation capabilities of Kubernetes knowledge; and to fine-tune the parameters of the retrained LLM pre-trained model to improve the versatility and correctness of the solutions provided by the LLM pre-trained model.

[0103] The deployment module is used to deploy the finely tuned LLM pre-trained model's LLM large model service, the AI ​​middleware service involving large model interaction, and the intelligent container cloud management console system on the Kubernetes cluster;

[0104] The intelligent function module is used to enable the intelligent container cloud management console system to interact with the fine-tuned LLM pre-trained model through the AI ​​middleware service. Based on the output of the LLM pre-trained model, it provides the following 7 intelligent functions: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestions, network topology optimization suggestions, pipeline compilation error analysis, alarm analysis and provision of handling methods.

[0105] The feedback module is used for production environment feedback and data return; after being automatically or manually filtered by the intelligent container cloud management console system, the returned data is added to the knowledge base.

[0106] The update module is used to update the knowledge base based on feedback and data feedback. The LLM pre-trained model is retrained based on the updated knowledge base. The LLM large model service, which redeploys the retrained LLM pre-trained model, continuously iterates and optimizes the model performance.

[0107] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described container cloud intelligent console implementation method.

[0108] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-described method for implementing a container cloud intelligent console.

[0109] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make several modifications and improvements without departing from the structure of the present invention, and these will not affect the effectiveness of the implementation of the present invention or the practicality of the patent.

Claims

1. A method for implementing a container cloud intelligent console, characterized in that, Includes the following steps: Step S1. Select the major LLM model type to be accessed; By adapting to various LLM large model interfaces, different LLM large models can be accessed, including open-source general large models on the Internet and industry large models. After determining the LLM pre-trained large model to be used, the access of the LLM large model can be completed by modifying the corresponding configuration file. Step S2. Build a Kubernetes knowledge base using a data collector; The data collector automatically collects large model instruction datasets in the Kubernetes cluster, and also collects knowledge data actively uploaded by users. The data collector integrates large model instruction datasets and user-uploaded knowledge data to form a knowledge base; Step S3. Based on the LLM pre-trained model, the LLM pre-trained model is retrained using the large model instruction dataset to enhance the LLM pre-trained model's ability to master, reason about, and generate Kubernetes knowledge; Step S4. Fine-tune the parameters of the retrained LLM pre-trained model to improve the versatility and correctness of the solution provided by the LLM pre-trained model; Step S5. Deploy the finely tuned LLM pre-trained model's LLM large model service, the AI ​​middleware service involving large model interaction, and the intelligent container cloud management console system on the Kubernetes cluster; Step S6. The intelligent container cloud management console system interacts with the fine-tuned LLM pre-trained model through the AI ​​middleware service, and provides the following 7 intelligent functions based on the output of the LLM pre-trained model: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestions, network topology optimization suggestions, pipeline compilation error analysis, alarm analysis and providing processing methods; Step S7. Perform production environment feedback and data feedback; Step S8. After automatic or manual filtering by the intelligent container cloud management console system, the returned data is added to the knowledge base; Step S9. Update the knowledge base based on feedback and data feedback, and retrain the LLM pre-trained model based on the updated knowledge base; Step S10. Redeploy the retrained LLM pre-trained model to the LLM large model service and continuously iterate and optimize the model performance; In step S7, feedback and data return include two forms: The first form is: when actively selecting recommended configuration items and using YAML completion, automatically submit the adoption status to the AI ​​middleware service to mark the data as approved; The second approach involves submitting an analysis and suggestions for the LLM pre-trained model. The intelligent container cloud management console system will then provide an option to agree with or disagree with the model's suggestions in the response. Users can choose based on the accuracy of the analysis and the reasonableness and effectiveness of the suggestions, thereby submitting data to the AI ​​platform service. Alternatively, users can upload their own responses for data feedback.

2. The method for implementing a container cloud intelligent console according to claim 1, characterized in that, In step S2, the large model instruction dataset includes Kubernetes official guidance, all YAML data of the current cluster, ETCD data, Kubernetes anomaly analysis and solutions on the Internet, and compilation and build error analysis and solutions.

3. The method for implementing a container cloud intelligent console according to claim 1, characterized in that, In step S2, the document data uploaded by the user and the custom knowledge data added by the user to the knowledge base are obtained; the document data includes Word files, PDF files and directly uploaded text data; the Word files and PDF files are parsed into text and included in the knowledge base together with the directly uploaded text data.

4. The method for implementing a container cloud intelligent console according to claim 1, characterized in that, In step S6, first select the question that needs to be submitted by the intelligent container cloud management console system to request the LLM pre-trained model, determine the category to which the question belongs, and then submit it to the corresponding large model Agent to process the intelligent function of the corresponding category.

5. The method for implementing a container cloud intelligent console according to claim 1, characterized in that, In step S6, the seven intelligent functions are as follows: Intelligent configuration recommendations: When creating Kubernetes resources using the wizard mode, the intelligent container cloud management console system automatically fills in some input boxes and highlights recommended options that need to be enabled or selected; Intelligent YAML Completion: When writing YAML files for Kubernetes to define Kubernetes resource objects, the intelligent container cloud management console system will automatically complete the YAML at the current cursor position. You can use a shortcut key to apply the YAML fragments added by intelligent YAML completion. Kubernetes Error Analysis: When an error event is reported in the container cloud console, the intelligent analysis function is triggered. The intelligent container cloud management console system will combine the current cluster content, official documentation, and solutions on the Internet to describe in detail the possible causes of the error and the corresponding solutions. Container application deployment optimization suggestions: Provide intelligent optimization suggestions for deployed applications to improve performance and resource utilization, making containerized application deployment more intelligent and efficient, and improving resource utilization and performance. Intelligent optimization suggestions include: adjusting the number of deployments, adding health checks, node affinity suggestions, node anti-affinity suggestions, and pod affinity suggestions; Network topology optimization suggestions: Provide optimization suggestions for service discovery methods, select optimization strategies suitable for the current architecture and business needs, effectively manage resources and reduce operation and maintenance costs; optimization suggestions include: service types, adjusting Pod distribution schemes; Pipeline Compilation Error Analysis: When a compilation error occurs during pipeline execution, the intelligent container cloud management console system generates a corresponding error log. The error log records the specific location of the error, the error code, and related context information. Through the pipeline compilation error analysis function, the root cause of the compilation error is accurately determined by analyzing the error log. Root causes include syntax problems, missing dependencies, and configuration errors. For each type of error, the intelligent container cloud management console system provides specific solutions, including code modification, dependency updates, and configuration adjustments. Alarm Analysis: The alarm analysis function can analyze historical alarm data to discover potential problem patterns and trends; and provide regularly generated alarm reports that summarize alarm events and their solutions in a recent period.

6. A container cloud intelligent console implementation system, characterized in that, include: The selection module is used to select the major types of LLM models to be accessed; By adapting to various LLM large model interfaces, different LLM large models can be accessed, including open-source general large models on the Internet and industry large models. After determining the LLM pre-trained large model to be used, the access of the LLM large model can be completed by modifying the corresponding configuration file. Create a knowledge base module to build a Kubernetes knowledge base using a data collector; The data collector automatically collects large model instruction datasets in the Kubernetes cluster, and also collects knowledge data actively uploaded by users. The data collector integrates large model instruction datasets and user-uploaded knowledge data to form a knowledge base; The training module is used to retrain the LLM pre-trained model using the large model instruction dataset, thereby enhancing the LLM pre-trained model's ability to master, reason about, and generate Kubernetes knowledge. Fine-tuning the parameters of the retrained LLM pre-trained model improves the versatility and correctness of the solutions provided by the LLM pre-trained model. The deployment module is used to deploy the finely tuned LLM pre-trained model's LLM large model service, the AI ​​middleware service involving large model interaction, and the intelligent container cloud management console system on the Kubernetes cluster; The intelligent function module is used to enable the intelligent container cloud management console system to interact with the fine-tuned LLM pre-trained model through the AI ​​middleware service, and provide the following 7 intelligent functions based on the output of the LLM pre-trained model: intelligent configuration recommendation, intelligent YAML completion, Kubernetes error analysis, container application deployment optimization suggestions, network topology optimization suggestions, pipeline compilation error analysis, alarm analysis and providing processing methods; The feedback module is used for production environment feedback and data feedback. After being automatically or manually filtered by the intelligent container cloud management console system, the returned data is added to the knowledge base. Feedback and data feedback include two forms: The first form is: when actively selecting recommended configuration items and using YAML completion, automatically submit the adoption status to the AI ​​middleware service to mark the data as approved; The second approach is as follows: After the LLM pre-trained model submits its analysis and suggestions, the intelligent container cloud management console system will provide an option below the response to either agree with or disagree with the large model's suggestions. Users can then choose based on whether the analysis is correct and whether the suggestions are reasonable and effective, thereby submitting data to the AI ​​platform service. Alternatively, users can upload their own responses for data feedback. The update module is used to update the knowledge base based on feedback and data feedback, and the LLM pre-trained model is retrained based on the updated knowledge base; The LLM large model service redeploys the retrained LLM pre-trained model and continuously iterates and optimizes the model performance.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements a container cloud intelligent console implementation method according to any one of claims 1-5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the container cloud intelligent console implementation method according to any one of claims 1-5.

Images