Joint debugging environment building method and device and related equipment
By automatically analyzing and handling microservice link failures through machine learning models, the problem of low efficiency in manual verification in existing technologies is solved, and the efficient construction of the joint debugging environment is achieved.
Patent Information
- Application Number
- CN202511688302.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-11-18
- Publication Date
- 2026-03-03
AI Technical Summary
In the process of setting up a microservice integration environment, existing technologies consume a lot of manpower by manually verifying the links between microservices, resulting in low efficiency.
Machine learning models are used to automatically analyze and process link failure information between microservices, generate solutions, and execute them to resolve link failures, ensuring the establishment of the joint debugging environment.
It improved the efficiency of setting up the joint debugging environment, reduced manual intervention, and enabled automated fault analysis and resolution.
Smart Images
Figure CN121603389A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of cloud computing technology, and in particular to a method, apparatus and related equipment for building a joint debugging environment. Background Technology
[0002] With the development of cloud computing technology, it has been applied in various fields. Microservices, in particular, are a method of designing applications as a set of small, independent services, each responsible for a specific function and capable of independent deployment and scaling. While microservices improve development efficiency, the setup of a joint debugging environment requires verifying the inter-service links due to the introduction of multiple different microservices. Current technologies typically rely on manual verification of these links when setting up a joint debugging environment for multiple microservices; however, this method consumes significant manpower and results in low efficiency. Summary of the Invention
[0003] To address the aforementioned technical problems, this invention provides a method, apparatus, and related equipment for building a joint debugging environment, which can effectively improve the efficiency of building a joint debugging environment.
[0004] To achieve the above objectives, the technical solution adopted in the embodiments of the present invention is as follows:
[0005] In a first aspect of this invention, a method for setting up a joint debugging environment is provided, the method comprising:
[0006] Multiple service systems and multiple transmission links are identified, with each transmission link being a transmission link between two of the service systems;
[0007] Link verification is performed on the multiple transmission links;
[0008] In the event of a failure in the target transmission link, a machine learning model is invoked to process the link failure information corresponding to the target transmission link, wherein the target transmission link is any one of the plurality of transmission links;
[0009] The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan.
[0010] If no one of the transmission links fails, generate the joint debugging environment corresponding to the multiple service systems.
[0011] Optionally, determining the multiple transmission links corresponding to multiple service systems includes:
[0012] Receive a setup request, which is used to generate a joint debugging environment for multiple service systems;
[0013] Based on the setup request, the connectivity relationship between the multiple service systems is determined. The connectivity relationship is used to indicate whether any two service systems are connected.
[0014] Based on the connectivity relationship, the plurality of transmission links are determined, and each transmission link is used to link the two corresponding service systems.
[0015] Optionally, before inputting the link failure information corresponding to the target transmission link into the machine learning model to process the link failure information based on the machine learning model when the target transmission link fails, the method further includes:
[0016] Obtain a training dataset, which includes multiple training samples, each of which includes a set of target link fault information and a target processing scheme corresponding to the target link fault information;
[0017] The initial machine learning model is trained based on the training dataset to obtain the trained machine learning model, wherein the initial machine learning model is a large language model.
[0018] Optionally, the step of invoking a machine learning model to process the link failure information corresponding to the target transmission link when a target transmission link fails includes:
[0019] When the link fault information corresponding to the target transmission link indicates that the target transmission link has missing call logs, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a first processing solution. The first processing solution includes calling an IP change tool to obtain the call logs.
[0020] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the first processing scheme.
[0021] Optionally, in the event of a failure in the target transmission link, inputting the link failure information corresponding to the target transmission link into a machine learning model to process the link failure information based on the machine learning model includes:
[0022] When the link fault information corresponding to the target transmission link indicates that the target transmission link has expired information, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a second processing solution. The second processing solution includes calling an information modification tool to modify the expired information.
[0023] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the second processing scheme.
[0024] Optionally, the link verification of the plurality of transmission links includes at least one of the following:
[0025] Functional verification was performed on the multiple transmission links;
[0026] Communication verification is performed on the multiple transmission links;
[0027] The functional verification is used to verify whether the corresponding transmission link includes the link transmission function, and the communication verification is used to verify whether the corresponding transmission link can transmit data normally.
[0028] In a second aspect of the present invention, a device for setting up a joint debugging environment is provided, the device comprising:
[0029] A determination module is used to determine multiple service systems and multiple transmission links, wherein each transmission link is a transmission link between two service systems;
[0030] The verification module is used to perform link verification on the multiple transmission links;
[0031] The processing module is used to call a machine learning model to process the link failure information corresponding to the target transmission link when the target transmission link fails, wherein the target transmission link is any one of the plurality of transmission links;
[0032] The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan.
[0033] The generation module is used to generate the joint debugging environment corresponding to the multiple service systems if no failure occurs in any of the transmission links.
[0034] In a third aspect of the embodiments of this application, an electronic device is also provided, including a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein when the program or instructions are executed by the processor, the steps of the method for building a joint debugging environment as described in any one of the first aspects are implemented.
[0035] In a fourth aspect of the embodiments of this application, a computer-readable storage medium is also provided, on which a program or instructions are stored, which, when executed by a processor, implement the steps of the method for building a joint debugging environment as described in any one of the first aspects.
[0036] In a fifth aspect of the embodiments of this application, the embodiments of this application also provide a computer program product, which is stored in a storage medium and is executed by at least one processor to implement the steps of the method for building a joint debugging environment as described in any one aspect of the first application.
[0037] This application provides a method, apparatus, and related equipment for building a joint debugging environment. The method includes: determining multiple transmission links corresponding to multiple service systems, each transmission link being a transmission link between two service systems; sequentially verifying the multiple transmission links; in the event of a target transmission link failure, invoking a machine learning model to process the link failure information corresponding to the target transmission link; wherein the machine learning model is used to analyze the input link failure information, generate a processing scheme for processing the link failure information, and execute the processing scheme; the target transmission link is any one of the multiple transmission links; and if the link verification corresponding to any one of the transmission links passes, generating a joint debugging environment corresponding to the multiple service systems. This application verifies multiple transmission links between multiple service systems, and in the event of a target transmission link failure, processes the link failure information corresponding to the target transmission link using a machine learning model, thereby completing the verification of all transmission links. This allows for automatic analysis of multiple transmission links, automatic fault resolution in the event of a failure, and generation of a joint debugging environment corresponding to multiple service systems while ensuring no transmission link failures, effectively improving the efficiency of building a joint debugging environment. Attached Figure Description
[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below.
[0039] Figure 1 This is a flowchart illustrating the method for setting up the integration testing environment in the embodiments of this application;
[0040] Figure 2 This is a schematic diagram illustrating the links between multiple service systems in an embodiment of this application;
[0041] Figure 3 This is a schematic diagram illustrating the process of setting up the integration testing environment in the embodiments of this application;
[0042] Figure 4 This is a schematic diagram of the structure of the setup device for the joint debugging environment in the embodiments of this application;
[0043] Figure 5 This is a schematic diagram of the structure of the electronic device in the embodiments of this application. Detailed Implementation
[0044] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0045] Before discussing the exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe the steps as sequential processes, many of these steps can be performed in parallel, concurrently, or simultaneously. Furthermore, the order of the steps can be rearranged. A process can be terminated when its operation is complete, but it may also have additional steps not included in the figures. A process can correspond to a method, function, procedure, subroutine, subroutine, etc.
[0046] Furthermore, the terms "first," "second," etc., may be used herein to describe various directions, actions, steps, or elements, but these directions, actions, steps, or elements are not limited by these terms. These terms are only used to distinguish one direction, action, step, or element from another direction, action, step, or element. For example, without departing from the scope of this application, a first string may be referred to as a second string, and similarly, a second string may be referred to as a first string. Both the first string and the second string are order requests, but they are not the same order request. The terms "first," "second," etc., should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0047] This application provides a method for setting up a joint debugging environment, such as... Figure 1 As shown, the method includes:
[0048] Step 101: Identify multiple service systems and multiple transmission links, where each transmission link is a transmission link between two service systems.
[0049] In this embodiment, multiple service systems can be microservices. A microservice is a method of designing an application as a set of small, independent services, each responsible for a specific function and capable of independent deployment and scaling. For example, ... Figure 2 As shown, this embodiment contains four microservices: A, B, C, and D. A joint debugging environment for these four microservices needs to be built. Among them, [the following is a list of components / mechanisms]... Figure 2 As we can see, only systems A and D require modification, while systems B and C remain unchanged. However, the functionality of this requirement depends on the interfaces of systems B and C, so it's essential to ensure that all links are connected, including the transmission links between A and B, B and C, and C and D. It should be noted that since there is no direct link between A and D, there is no transmission link between A and D.
[0050] Step 102: Perform link verification on the multiple transmission links.
[0051] In this embodiment, link verification between services typically involves multiple aspects to ensure normal and effective communication between services. Exemplary methods may include the following: Log tracing: Using a distributed logging system (such as ELK Stack, Fluentd, etc.) to record requests and responses between microservices for subsequent analysis. Adding unique identifiers (such as trace IDs) to requests helps track the flow of requests between different services. Link tracing: Using link tracing tools (such as Jaeger, Zipkin, OpenTracing, etc.) to collect and visualize link information of calls between microservices. These tools can display call relationships, latency, and failure scenarios between different services. Health checks: Implementing a health check interface for each microservice, and periodically checking service availability using monitoring tools (such as Spring Boot Actuator, Kubernetes, etc.). Monitoring service status and response time to promptly identify problems. API gateway: Using an API gateway to uniformly manage microservice traffic, supporting functions such as load balancing, rate limiting, and circuit breaking. The API gateway can record call logs and provide certain monitoring and link tracing capabilities. Performance testing: Conduct performance tests regularly, using load testing tools (such as JMeter, Gatling, etc.) to check the service's performance under high load and verify the performance of links between services.
[0052] Step 103: In the event of a failure in the target transmission link, a machine learning model is invoked to process the link failure information corresponding to the target transmission link, wherein the target transmission link is any one of the plurality of transmission links; wherein the machine learning model is used to analyze the link failure information, generate a processing plan for processing the link failure information, and execute the processing plan.
[0053] In this embodiment, the target transmission link is any one of the transmission links between AB, BC, and CD. Specifically, when the target transmission link fails, link failure information is generated. The link failure information may include the cause of the link failure, such as a functional failure or a communication failure, etc., which is not specifically limited in this embodiment.
[0054] The machine learning model is a pre-trained model, such as a Large Language Model (LLM). A LLM is a natural language processing model based on deep learning technology, capable of processing, generating, and understanding natural language. These models typically have a large number of parameters and a huge training dataset, enabling them to capture syntactic, semantic, and contextual information in natural language. By inputting link failure information into the machine learning model for analysis, a corresponding processing solution is generated and automatically executed. This process requires no manual intervention; the trained machine learning model automatically processes the link failure information. After processing, the link failure information corresponding to the target transmission link can be uploaded and saved so that it can be resolved promptly if the same failure occurs again.
[0055] It should also be noted that when all transmission links are functioning correctly, the next step can be taken directly to generate the joint debugging environment for multiple service systems.
[0056] Step 104: If no failure occurs in any of the transmission links, generate the joint debugging environment corresponding to the multiple service systems.
[0057] In this embodiment, after all transmission links pass verification, a joint debugging environment corresponding to multiple service systems is generated. Passing link verification means that no transmission link experiences a failure, or that a failure has been resolved. Specifically, the joint debugging system for multiple microservices typically refers to a comprehensive development and testing environment used for integrating, debugging, and coordinating multiple microservices. This joint debugging environment helps developers and testers ensure normal interaction between services, improves development efficiency, and reduces problems caused by service incompatibility.
[0058] This application verifies multiple transmission links between multiple service systems. In the event of a failure in a target transmission link among these multiple transmission links, a machine learning model is used to process the link failure information corresponding to the target transmission link, thereby completing the verification of all transmission links. This allows for automatic analysis of multiple transmission links and automatic resolution of failures in the event of a failure. Under the condition that no transmission links are faulty, a joint debugging environment corresponding to multiple service systems is generated, effectively improving the efficiency of building a joint debugging environment.
[0059] Optionally, determining multiple service systems and multiple transmission links includes:
[0060] Receive a setup request, which is used to generate a joint debugging environment for multiple service systems;
[0061] Based on the setup request, the connectivity relationship between the multiple service systems is determined. The connectivity relationship is used to indicate whether any two service systems are connected.
[0062] Based on the connectivity relationship, the plurality of transmission links are determined, and each transmission link is used to link the two corresponding service systems.
[0063] After receiving a setup request on the server side, the request may contain information such as the type and quantity of services to be set up, the specific configuration requirements, environment requirements, and version. Setup requests can be received via an API interface, with the interface parameters explicitly specifying the detailed request information. It should also be noted that requests can be transmitted in JSON format to ensure flexibility and scalability.
[0064] Analyze the dependencies between multiple service systems to identify which services can directly transfer data. For example, a service dependency graph can be constructed to understand which other services each service needs to call. This graph can be defined through configuration files or service development documentation. Determine the API interfaces between services, including request and response formats, to support the corresponding data transfer.
[0065] After analyzing the relationships between services, the system can identify multiple transmission links, i.e., which services can communicate with each other, thereby accurately determining the joint debugging environment corresponding to multiple service systems.
[0066] By analyzing the dependencies between services, it is ensured that suitable transport links can be established. This process requires consideration of multiple aspects during system design, including architecture design, service registration, health checks, dynamic configuration, monitoring, and log management. Through these steps, efficient interaction and coordination of the microservice system can be ensured, improving development and debugging efficiency.
[0067] Optionally, before inputting the link failure information corresponding to the target transmission link into the machine learning model to process the link failure information based on the machine learning model when the target transmission link fails, the method further includes:
[0068] Obtain a training dataset, which includes multiple training samples, each of which includes a set of target link fault information and a target processing scheme corresponding to the target link fault information;
[0069] The initial machine learning model is trained based on the training dataset to obtain the trained machine learning model, wherein the initial machine learning model is a large language model.
[0070] In this embodiment, before using the machine learning model, it is necessary to train the machine learning model using a training dataset. The training dataset includes multiple training samples. Specifically, each training sample includes a set of target link fault information and a target processing scheme corresponding to the target link fault information.
[0071] The training process can adjust the model's parameters through optimization algorithms (such as gradient descent) to enable it to better understand and generate natural language. Once training is complete, the resulting model is a trained machine learning model. It has learned how to process and generate language through the analysis of large amounts of data and can be applied to specific tasks (such as text classification, generation, question answering, etc.).
[0072] It's worth noting that large language models were chosen because they are typically massive in scale, containing hundreds of millions of parameters, and capable of capturing complex language patterns and contextual relationships. This makes them perform exceptionally well in Natural Language Processing (NLP) tasks.
[0073] Optionally, the step of invoking a machine learning model to process the link failure information corresponding to the target transmission link when a target transmission link fails includes:
[0074] When the link fault information corresponding to the target transmission link indicates that the target transmission link has missing call logs, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a first processing solution. The first processing solution includes calling an IP change tool to obtain the call logs.
[0075] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the first processing scheme.
[0076] In this embodiment, link failure information includes various data or event records related to the link failure. This information can be logs, error codes, or other data indicating the link status. Missing call logs refer to situations where critical call logs are missing from the link failure information, which will affect the diagnosis and handling of the failure. Call logs generally record system operations and their results, and are an important basis for troubleshooting.
[0077] After identifying a fault in the target transmission link, this information is input into a machine learning model for analysis. The machine learning model is trained to identify patterns, analyze data, and generate response plans. After analyzing the input link fault information, the machine learning model outputs a first processing plan. Specifically, this first processing plan is derived based on the current fault information, aiming to find appropriate handling measures. Calling the IP change tool refers to retrieving missing call logs. Changing the IP may allow the system to regenerate or collect relevant logs for further, more in-depth fault analysis. Once the first processing plan is generated, the machine learning model is called again, and the fault information of the target transmission link is processed based on this plan.
[0078] Therefore, when network links fail, machine learning models can be used efficiently for fault analysis and handling. By analyzing link fault information, a handling plan can be generated, and then appropriate tools can be used to supplement the necessary data, ultimately improving the effectiveness and speed of fault handling.
[0079] Optionally, in the event of a failure in the target transmission link, inputting the link failure information corresponding to the target transmission link into a machine learning model to process the link failure information based on the machine learning model includes:
[0080] When the link fault information corresponding to the target transmission link indicates that the target transmission link has expired information, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a second processing solution. The second processing solution includes calling an information modification tool to modify the expired information.
[0081] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the second processing scheme.
[0082] In this embodiment, link failure information is input into the machine learning model. This link failure information includes various types of data related to network link operation, as well as the specific context of the failure. Specifically, expired information is detected by the model within the link failure information. Expired information refers to old or invalid configuration, data, or status information that may lead to network link failure. By analyzing the input link failure information, the machine learning model generates a second processing scheme. Specifically, the second processing scheme addresses the identified expired information issue and proposes a solution.
[0083] The second processing solution involves invoking an information modification tool to correct outdated link information. By updating or replacing expired information, the link's normal operation can be restored. Following the second processing solution, the machine learning model is invoked again. This is done to further analyze and process the fault information according to the new solution, ensuring the link fault is effectively resolved.
[0084] Therefore, in link fault diagnosis, machine learning models are used to identify outdated information, generate and implement corresponding handling solutions, and then utilize the machine learning model again to optimize and verify the link status. This demonstrates the role of machine learning in network management and fault handling, ensuring network reliability and stability.
[0085] Optionally, the link verification of the plurality of transmission links includes at least one of the following:
[0086] Functional verification was performed on the multiple transmission links;
[0087] Communication verification is performed on the multiple transmission links;
[0088] The functional verification is used to verify whether the corresponding transmission link includes the link transmission function, and the communication verification is used to verify whether the corresponding transmission link can transmit data normally.
[0089] In this embodiment, link verification refers to the actual testing and evaluation of these transmission links to ensure they function correctly as expected. This process is an important part of network management and maintenance, as link failures directly affect the availability and performance of network services.
[0090] Specifically, functional verification is used to confirm whether each transmission link possesses the required link transmission functions. Specifically, functional verification checks whether the link can perform the basic operations it promises, such as data encapsulation and decapsulation, and other necessary link management functions. Communication verification is used to determine whether the link can transmit data normally. This includes checking whether packet sending and receiving are smooth, and whether there are problems such as delays or packet loss.
[0091] Systematic verification of multiple transmission links ensures their proper functioning. Functional verification focuses on whether the required functions of the link are implemented, while communication verification emphasizes the effectiveness of data transmission. This verification process is crucial for maintaining network health and optimizing performance.
[0092] like Figure 3 As shown, Figure 3This is a schematic diagram illustrating the process of setting up the integration testing environment in this embodiment. When the integration testing environment needs to be generated on the server, four service systems, A, B, C, and D, are used as examples for explanation. Figure 2 As shown, there are links between A and B, between A and C, and between C and D. The links between A and B, B and C, and C and D are verified sequentially.
[0093] Specifically, if the link between A and B fails verification, a machine learning model (AI) is used to identify and resolve the problem. If the machine learning model cannot resolve the issue, a responsible person resolves it manually, and the solution is stored in a knowledge base so that the machine learning model can automatically resolve the same problem the next time it is encountered. The same principle applies to the links between B and C, and between C and D.
[0094] It should be noted that the link between A and B is verified first. After the link between A and B is verified, the link between B and C is verified, and then the link between C and D is verified. This ensures that the verification is completed sequentially according to the relationship between the service systems, thus ensuring verification efficiency.
[0095] In this embodiment, the verification process can be fully automated by a machine learning model. Only when the machine learning model cannot handle the process will manual intervention be required. Therefore, the technical solution of this application can effectively improve the efficiency of building a joint debugging environment.
[0096] This application verifies multiple transmission links between multiple service systems. In the event of a failure in a target transmission link among these multiple transmission links, a machine learning model is used to process the link failure information corresponding to the target transmission link, thereby completing the verification of all transmission links. This allows for automatic analysis of multiple transmission links and automatic resolution of failures in the event of a failure. Under the condition that no transmission links are faulty, a joint debugging environment corresponding to multiple service systems is generated, effectively improving the efficiency of building a joint debugging environment.
[0097] This application provides a device for setting up a joint debugging environment, such as... Figure 4 As shown, the setup device 400 for the commissioning environment includes:
[0098] The determination module 410 is used to determine multiple service systems and multiple transmission links, wherein each transmission link is a transmission link between two service systems;
[0099] Verification module 420 is used to perform link verification on the plurality of transmission links;
[0100] Processing module 430 is used to call a machine learning model to process the link failure information corresponding to the target transmission link when the target transmission link fails, wherein the target transmission link is any one of the plurality of transmission links;
[0101] The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan.
[0102] The generation module 440 is used to generate the joint debugging environment corresponding to the multiple service systems when no failure occurs in any of the transmission links.
[0103] Optionally, the determining module 410 includes:
[0104] The receiving submodule is used to receive setup requests, which are used to generate joint debugging environments for multiple service systems.
[0105] The first determining submodule is used to determine the connectivity relationship between the multiple service systems based on the building request. The connectivity relationship is used to indicate whether any two service systems are connected among the multiple service systems.
[0106] The second determining submodule is used to determine the plurality of transmission links based on the connectivity relationship, wherein each transmission link is used to link the corresponding two service systems.
[0107] Optional, also includes:
[0108] The acquisition module is used to acquire a training dataset, which includes multiple training samples. Each training sample includes a set of target link fault information and a target processing scheme corresponding to the target link fault information.
[0109] The training module is used to train the initial machine learning model based on the training dataset to obtain the trained machine learning model, wherein the initial machine learning model is a large language model.
[0110] Optionally, the processing module 430 includes:
[0111] The first analysis submodule is used to input the link fault information corresponding to the target transmission link into a machine learning model when the link fault information corresponding to the target transmission link indicates that the target transmission link has missing call logs, analyze the link fault information, and generate a first processing solution. The first processing solution includes calling an IP change tool to obtain the call logs.
[0112] The first processing submodule is used to invoke the machine learning model to process the link fault information corresponding to the target transmission link based on the first processing scheme.
[0113] Optionally, the processing module 430 includes:
[0114] The second analysis submodule is used to input the link fault information corresponding to the target transmission link into a machine learning model when the link fault information corresponding to the target transmission link indicates that the target transmission link has expired information, analyze the link fault information, and generate a second processing scheme. The second processing scheme includes calling an information modification tool to modify the expired information.
[0115] The second processing submodule is used to invoke the machine learning model to process the link fault information corresponding to the target transmission link based on the second processing scheme.
[0116] Optionally, the verification module 420 includes:
[0117] The first verification submodule is used to perform functional verification on the multiple transmission links;
[0118] The second verification submodule is used to perform communication verification on the multiple transmission links;
[0119] The functional verification is used to verify whether the corresponding transmission link includes the link transmission function, and the communication verification is used to verify whether the corresponding transmission link can transmit data normally.
[0120] This application verifies multiple transmission links between multiple service systems. In the event of a failure in a target transmission link among these multiple transmission links, a machine learning model is used to process the link failure information corresponding to the target transmission link, thereby completing the verification of all transmission links. This allows for automatic analysis of multiple transmission links and automatic resolution of failures in the event of a failure. Under the condition that no transmission links are faulty, a joint debugging environment corresponding to multiple service systems is generated, effectively improving the efficiency of building a joint debugging environment.
[0121] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application, such as... Figure 5 As shown, the electronic device 500 includes a memory 510 and a processor 520. The number of processors 520 in the electronic device 500 can be one or more. Figure 5 Taking a processor 520 as an example; the memory 510 and processor 520 in the server can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.
[0122] The memory 510, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the member push method in the embodiments of this application. The processor 520 executes various functional applications and data processing of the server / terminal / server by running the software programs, instructions, and modules stored in the memory 510, thereby realizing the above-mentioned method for building the joint debugging environment.
[0123] The processor 520 is used to run the computer program stored in the memory 510, and performs the following steps:
[0124] Multiple service systems and multiple transmission links are identified, with each transmission link being a transmission link between two of the service systems;
[0125] Link verification is performed on the multiple transmission links;
[0126] In the event of a failure in the target transmission link, a machine learning model is invoked to process the link failure information corresponding to the target transmission link, wherein the target transmission link is any one of the plurality of transmission links;
[0127] The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan.
[0128] If no one of the transmission links fails, generate the joint debugging environment corresponding to the multiple service systems.
[0129] Optionally, determining the multiple transmission links corresponding to multiple service systems includes:
[0130] Receive a setup request, which is used to generate a joint debugging environment for multiple service systems;
[0131] Based on the setup request, the connectivity relationship between the multiple service systems is determined. The connectivity relationship is used to indicate whether any two service systems are connected.
[0132] Based on the connectivity relationship, the plurality of transmission links are determined, and each transmission link is used to link the two corresponding service systems.
[0133] Optionally, before inputting the link failure information corresponding to the target transmission link into the machine learning model to process the link failure information based on the machine learning model when the target transmission link fails, the method further includes:
[0134] Obtain a training dataset, which includes multiple training samples, each of which includes a set of target link fault information and a target processing scheme corresponding to the target link fault information;
[0135] The initial machine learning model is trained based on the training dataset to obtain the trained machine learning model, wherein the initial machine learning model is a large language model.
[0136] Optionally, the step of invoking a machine learning model to process the link failure information corresponding to the target transmission link when a target transmission link fails includes:
[0137] When the link fault information corresponding to the target transmission link indicates that the target transmission link has missing call logs, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a first processing solution. The first processing solution includes calling an IP change tool to obtain the call logs.
[0138] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the first processing scheme.
[0139] Optionally, in the event of a failure in the target transmission link, inputting the link failure information corresponding to the target transmission link into a machine learning model to process the link failure information based on the machine learning model includes:
[0140] When the link fault information corresponding to the target transmission link indicates that the target transmission link has expired information, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a second processing solution. The second processing solution includes calling an information modification tool to modify the expired information.
[0141] The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the second processing scheme.
[0142] Optionally, the link verification of the plurality of transmission links includes at least one of the following:
[0143] Functional verification was performed on the multiple transmission links;
[0144] Communication verification is performed on the multiple transmission links;
[0145] The functional verification is used to verify whether the corresponding transmission link includes the link transmission function, and the communication verification is used to verify whether the corresponding transmission link can transmit data normally.
[0146] This application verifies multiple transmission links between multiple service systems. In the event of a failure in a target transmission link among these multiple transmission links, a machine learning model is used to process the link failure information corresponding to the target transmission link, thereby completing the verification of all transmission links. This allows for automatic analysis of multiple transmission links and automatic resolution of failures in the event of a failure. Under the condition that no transmission links are faulty, a joint debugging environment corresponding to multiple service systems is generated, effectively improving the efficiency of building a joint debugging environment.
[0147] The computer-readable storage medium of this application embodiment can be any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. For example, a computer-readable storage medium can be—but is not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0148] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.
[0149] The program code contained on the storage medium can be transmitted using any suitable medium, including—but not limited to—wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.
[0150] Computer program code for performing the operations of this application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or terminal. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0151] This application also provides a computer program product, which is stored in a storage medium and executed by at least one processor to implement the various processes of the above-described method for building the joint debugging environment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.
[0152] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the appended claims.
Claims
1. A method for setting up a joint debugging environment, characterized in that, The method includes: Multiple service systems and multiple transmission links are identified, with each transmission link being a transmission link between two of the service systems; Link verification is performed on the multiple transmission links; In the event of a failure in the target transmission link, a machine learning model is invoked to process the link failure information corresponding to the target transmission link, wherein the target transmission link is any one of the plurality of transmission links; The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan. If no one of the transmission links fails, generate the joint debugging environment corresponding to the multiple service systems.
2. The method according to claim 1, characterized in that, The determination of multiple service systems and multiple transmission links includes: Receive a setup request, which is used to generate a joint debugging environment for multiple service systems; Based on the setup request, the connectivity relationship between the multiple service systems is determined. The connectivity relationship is used to indicate whether any two service systems are connected. Based on the connectivity relationship, the plurality of transmission links are determined, and each transmission link is used to link the two corresponding service systems.
3. The method according to claim 1, characterized in that, Before inputting the link failure information corresponding to the target transmission link into the machine learning model to process the link failure information based on the machine learning model in the event of a failure of the target transmission link, the method further includes: Obtain a training dataset, which includes multiple training samples, each of which includes a set of target link fault information and a target processing scheme corresponding to the target link fault information; The initial machine learning model is trained based on the training dataset to obtain the trained machine learning model, wherein the initial machine learning model is a large language model.
4. The method according to claim 1, characterized in that, In the event of a failure in the target transmission link, the process of calling a machine learning model to handle the link failure information corresponding to the target transmission link includes: When the link fault information corresponding to the target transmission link indicates that the target transmission link has missing call logs, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a first processing solution. The first processing solution includes calling an IP change tool to obtain the call logs. The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the first processing scheme.
5. The method according to claim 1, characterized in that, In the event of a failure in the target transmission link, the link failure information corresponding to the target transmission link is input into a machine learning model to process the link failure information based on the machine learning model, including: When the link fault information corresponding to the target transmission link indicates that the target transmission link has expired information, the link fault information corresponding to the target transmission link is input into a machine learning model to analyze the link fault information and generate a second processing solution. The second processing solution includes calling an information modification tool to modify the expired information. The machine learning model is invoked to process the link fault information corresponding to the target transmission link based on the second processing scheme.
6. The method according to any one of claims 1-5, characterized in that, The link verification of the plurality of transmission links includes at least one of the following: Functional verification was performed on the multiple transmission links; Communication verification is performed on the multiple transmission links; The functional verification is used to verify whether the corresponding transmission link includes the link transmission function, and the communication verification is used to verify whether the corresponding transmission link can transmit data normally.
7. A device for constructing a commissioning environment, characterized in that, The device includes: A determination module is used to determine multiple service systems and multiple transmission links, wherein each transmission link is a transmission link between two service systems; The verification module is used to perform link verification on the multiple transmission links; The processing module is used to call a machine learning model to process the link failure information corresponding to the target transmission link when the target transmission link fails, wherein the target transmission link is any one of the plurality of transmission links; The machine learning model is used to analyze the link failure information, generate a processing plan for the link failure information, and execute the processing plan. The generation module is used to generate the joint debugging environment corresponding to the multiple service systems if no failure occurs in any of the transmission links.
8. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the method for building a joint debugging environment as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the method for building a joint debugging environment as described in any one of claims 1 to 6.
10. A computer program product, characterized in that, The computer program product is stored in a storage medium, and the computer program product is executed by at least one processor to implement the steps in the method for building a joint debugging environment as described in any one of claims 1 to 6.