Software online environment self-checking method, device and equipment and storage medium

Abstract

The invention relates to the technical field of financial science and technology, in particular to a software online environment self-checking method, device and equipment and a storage medium, and the method comprises the following steps: inputting an obtained online environment configuration file into a large language model for processing to obtain a high-dimensional semantic vector; obtaining configuration key elements based on the high-dimensional semantic vector and a named entity recognition model; generating a corresponding self-checking task based on the configuration key element; and executing the self-checking task to obtain a corresponding self-checking result. According to the method, the verification effect and verification efficiency of software online environment inspection can be conveniently improved.

Description

Technical Field

[0001] The present application relates to the field of financial technology, and in particular to a method, device, equipment and storage medium for self-checking a software online environment. Background Art

[0002] In order to provide better services to users, banks generally develop their own banking software, such as mobile banking APP. After the development or version optimization of the banking software is completed, the banking software needs to be deployed to the corresponding operating environment for providing external services, which is also the software online environment. In order to ensure the success rate of banking software deployment, before deploying the banking software to the software online environment, the software online environment needs to be checked to determine whether the software online environment has currently completed the preparations for the deployment of the banking software.

[0003] At present, the software online environment is generally checked manually. Specifically, the operation and maintenance personnel maintain the environment variables according to the deployment manual. If there are steps to manually operate the server, log in to the server to execute the operation and maintenance commands and initialize the environment; the developer refers to the test environment and uploads the shell script for product environment verification to the Devops system; the operation and maintenance personnel operate in the Devops system and send the self-check script to the online environment server; the operation and maintenance personnel operate in the Devops system and execute the self-check script before installation to verify the environmental verification of the online environment.

[0004] However, on the one hand, developers cannot directly view the configuration of the online environment, such as file directory structure, disk space, directory permissions, etc., which causes the verification script to miss the verification of the online environment; on the other hand, some software products need to rely on pre-processes / pre-systems before installation and deployment, but when operation and maintenance personnel operate and deploy in the Devops system, they automatically execute the installation steps and cannot detect whether the pre-dependencies are ready, resulting in installation failure; in summary, the verification effect and efficiency of software online environment checks using existing technologies are poor. Summary of the invention

[0005] In order to improve the verification effect and verification efficiency of software online environment inspection, the present application provides a software online environment self-inspection method, device, equipment and storage medium.

[0006] In a first aspect, the present application provides a software online environment self-check method, comprising:

[0007] Input the obtained online environment configuration file into the large language model to obtain a high-dimensional semantic vector;

[0008] Obtaining configuration key elements based on the high-dimensional semantic vector and the named entity recognition model;

[0009] Generate corresponding self-check tasks based on the configuration key elements;

[0010] Execute the self-check task to obtain a corresponding self-check result.

[0011] Through the above implementation, the online environment configuration file can be processed through the large language model and the named entity recognition model to generate a self-check task, and there will be no situation where the verification script is manually omitted, which helps to fully improve the verification effect of the software online environment inspection; in addition, the software online environment self-check method is fully automated, which greatly reduces the dependence on manual labor and does not need to rely on front-end processes / front-end systems, thereby facilitating the full improvement of the verification efficiency of the software online environment inspection.

[0012] Preferably, the step of inputting the acquired online environment configuration file into a large language model to obtain a high-dimensional semantic vector includes:

[0013] Segmenting the online environment configuration file to obtain configuration file segmentation;

[0014] The configuration file word segmentation is input into a large language model for processing to obtain a high-dimensional semantic vector.

[0015] Through the above implementation, the online environment configuration file is first segmented, and then the configuration file segmentation is processed through a large language model, which makes it easy to improve the accuracy of the generated high-dimensional semantic vector.

[0016] Preferably, the configuration key elements are obtained based on the high-dimensional semantic vector and the named entity recognition model, including:

[0017] Input the preset recognition prompt words into the named entity recognition model;

[0018] The high-dimensional semantic vector is processed based on the named entity recognition model input with the recognition prompt word to obtain configuration key elements.

[0019] Through the above implementation, the high-dimensional semantic vector is processed by the named entity recognition model with recognition prompt words, which makes it easy to improve the accuracy of the output configuration key elements.

[0020] Preferably, the key configuration elements include: file directory, user name, IP address and port configuration.

[0021] Through the above implementation, the specific content of the configuration key elements is disclosed, so that the scope of the configuration key elements can be clearly defined.

[0022] Preferably, the software online environment self-checking method provided by the present application further includes:

[0023] In response to the self-check result indicating that all the self-check tasks have been executed successfully, the software is deployed to the online environment corresponding to the online environment configuration file.

[0024] Through the above implementation, when all self-check tasks are executed and passed, the software is deployed to the online environment, which makes it easy to improve the stability of software deployment.

[0025] Preferably, the software online environment self-checking method provided by the present application further includes:

[0026] In response to the self-check result indicating that the self-check task has not been fully executed, reconfiguring the online environment corresponding to the online environment configuration file based on the self-check result to obtain a new online environment;

[0027] A new online environment configuration file of the new online environment is obtained, and a new self-check result is obtained based on the new online environment configuration file, until the self-check result indicates that all the self-check tasks have been executed successfully.

[0028] Through the above implementation, if all self-check tasks are not executed successfully, the online environment is reconfigured and the method is re-executed in a loop, so as to ensure the continuity of the online environment self-check.

[0029] In a second aspect, the present application provides a software online environment self-checking device, comprising:

[0030] A vector acquisition module is used to input the acquired online environment configuration file into the large language model to obtain a high-dimensional semantic vector;

[0031] An element acquisition module, used to obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model;

[0032] A task generation module, used to generate corresponding self-check tasks based on the configuration key elements;

[0033] The result generation module is used to execute the self-check task to obtain the corresponding self-check result.

[0034] Through the above implementation, the online environment configuration file can be processed through the large language model and the named entity recognition model to generate a self-check task, and there will be no situation where the verification script is manually omitted, which helps to fully improve the verification effect of the software online environment inspection; in addition, the software online environment self-check method is fully automated, which greatly reduces the dependence on manual labor and does not need to rely on front-end processes / front-end systems, thereby facilitating the full improvement of the verification efficiency of the software online environment inspection.

[0035] In a third aspect, the present application provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method when executing the computer program.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the above method when executed by a processor.

[0037] In a fifth aspect, the present application further provides a computer program product, wherein the computer program product comprises a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0038] The above-mentioned software online environment self-check method, device, equipment and storage medium obtain a high-dimensional semantic vector by inputting the obtained online environment configuration file into a large language model; obtaining configuration key elements based on the high-dimensional semantic vector and the named entity recognition model; generating corresponding self-check tasks based on the configuration key elements; and executing the self-check tasks to obtain corresponding self-check results. Through the above implementation, the online environment configuration file can be processed by the large language model and the named entity recognition model to generate a self-check task, and there will be no situation where the verification script is manually omitted, which helps to fully improve the verification effect of the software online environment inspection. In addition, the software online environment self-check method is fully automatically executed, which greatly reduces the dependence on manual labor, and does not need to rely on front-end processes / front-end systems, etc., so as to fully improve the verification efficiency of the software online environment inspection.

[0039] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 A flowchart of a software online environment self-checking method provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of another software online environment self-checking method provided in an embodiment of the present application;

[0043] Figure 3A flowchart of another software online environment self-checking method provided in an embodiment of the present application;

[0044] Figure 4 A schematic diagram of the structure of a software online environment self-checking device provided in an embodiment of the present application;

[0045] Figure 5 A schematic diagram of the structure of another software online environment self-checking device provided in an embodiment of the present application;

[0046] Figure 6 A structural diagram of another software online environment self-checking device provided in an embodiment of the present application;

[0047] Figure 7 A schematic diagram of the structure of a computer device provided in an embodiment of the present application;

[0048] Figure 8 This is a diagram of the internal structure of a computer-readable storage medium provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solution and advantages of the present disclosure more clear, the present disclosure is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present disclosure and are not used to limit the present disclosure.

[0050] It should be noted that the terms "first", "second", etc. in the specification and claims of this article and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this article described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0051] In this article, the term "and / or" is only a description of the association relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the related objects before and after are in an "or" relationship.

[0052] Embodiment 1

[0053] Figure 1A flowchart of a software online environment self-checking method provided in Example 1 of the present application, refer to Figure 1 The method may be performed by a device for performing the method, and the device may be implemented by software and / or hardware. The method includes:

[0054] S110, inputting the obtained online environment configuration file into a large language model to obtain a high-dimensional semantic vector.

[0055] Among them, the online environment configuration file is a file used to define various parameters and settings required for the software to run in the formal production environment (i.e., the online environment). The online environment configuration file is used to guide the software on how to correctly use the resources in various online environments and run according to specific rules; in this embodiment, the content of the online environment configuration file specifically includes: database connection information, server configuration, third-party service integration configuration, log configuration, and security configuration, which are not specifically limited in other embodiments; the online environment configuration file is the configuration file of the online environment of the bank software in this embodiment; the online environment is the operating environment for the software to be officially deployed and provide services to the outside after the software is developed, and it is the final operating place for the software product to transition from the development and testing stage to the actual use stage. The large language model is used to process the online environment configuration file in text form, and output the high-dimensional semantic vector corresponding to the online environment configuration file. The high-dimensional semantic vector is used to represent the part of speech, word frequency, and semantic information of the words in the online environment configuration file.

[0056] Specifically, the online environment configuration file of the online environment is obtained by processing the preset large language model, so as to obtain a high-dimensional semantic vector corresponding to each word in the online environment configuration file.

[0057] S120. Obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model.

[0058] Among them, the named entity recognition model can process each high-dimensional semantic vector and output configuration key elements, which are the objects that need to be checked in the subsequent self-inspection of the online environment. For example, a configuration key element is the file directory of the online environment configuration file.

[0059] It should be noted that, in this embodiment, the configuration key elements output by the named entity recognition model are returned in JSON format.

[0060] Specifically, each high-dimensional semantic vector is input into a named entity recognition model for processing, and the named entity recognition model outputs one or more configuration key elements corresponding to each high-dimensional semantic vector.

[0061] S130: Generate a corresponding self-check task based on the configuration key elements.

[0062] Among them, the self-check task is generated based on the corresponding configuration key element, and the self-check task is used to implement the inspection of the corresponding configuration key element through subsequent execution; in the example row, the configuration key element is "file directory", and the self-check task generated based on the configuration key element is "check whether the file directory exists".

[0063] Specifically, a corresponding self-check task is generated based on the configuration key element; it should be noted that there are generally multiple self-check tasks.

[0064] S140: Execute the self-check task to obtain a corresponding self-check result.

[0065] Among them, the self-check result is the execution result of each check task, which can be used to characterize whether each check task has been executed successfully; the execution result is used to characterize whether a corresponding self-check task has been executed successfully; for example, if after completing the self-check task of "checking whether the file directory exists", it is determined that the check file directory exists, the execution result of the self-check task is that the self-check task has been executed successfully, otherwise, the execution result is that the self-check task has not been executed successfully.

[0066] Specifically, all the self-checking tasks are executed respectively, and the execution results corresponding to all the self-checking tasks are collected to obtain the self-checking results.

[0067] It should be noted that, in this embodiment, the obtained online environment configuration file is input into the large language model for processing to obtain a high-dimensional semantic vector; configuration key elements are obtained based on the high-dimensional semantic vector and the named entity recognition model; corresponding self-check tasks are generated based on the configuration key elements; and the self-check tasks are executed to obtain corresponding self-check results; through the above implementation, the online environment configuration file can be processed by the large language model and the named entity recognition model to generate self-check tasks, and there will be no situation where the verification script is manually omitted, which helps to fully improve the verification effect of the software online environment inspection; in addition, the software online environment self-check method is fully automatically executed, which greatly reduces the dependence on manual labor, and does not need to rely on front-end processes / front-end systems, etc., thereby facilitating the full improvement of the verification efficiency of the software online environment inspection.

[0068] Embodiment 2

[0069] A software online environment self-checking method provided in the second embodiment of the present application optimizes the "inputting the obtained online environment configuration file into the large language model to obtain a high-dimensional semantic vector" in the first embodiment; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and the method includes:

[0070] S211, segmenting the online environment configuration file to obtain configuration file segmentation.

[0071] Among them, the online environment configuration file is a text, and word segmentation means dividing this text into multiple words through a preset word segmentation library or word segmentation algorithm; the configuration file word segmentation refers to the words obtained after performing word segmentation on the online environment configuration file; after performing word segmentation on the online environment configuration file, multiple words after performing word segmentation on the online environment configuration file can be obtained.

[0072] Specifically, the preset word segmentation library or word segmentation algorithm performs word segmentation on the online environment configuration file, thereby obtaining multiple configuration file word segmentations.

[0073] It should be noted that there may be some stop words in the configuration file word segmentation. The so-called stop words refer to words with a relatively low contribution to understanding the key semantics of the online environment configuration file. Exemplarily, stop words include: "de", "le", punctuation marks, and modal particles, etc.; after obtaining the preliminary configuration file word segmentation by means of word segmentation on the online environment configuration file, the stop words in the preliminary configuration file word segmentation can be further screened out, thereby obtaining the target configuration file word segmentation.

[0074] S212. Input the configuration file word segmentation into a large language model for processing to obtain high-dimensional semantic vectors.

[0075] Among them, the large language model is used to process each configuration file word segmentation input into it and output high-dimensional semantic vectors corresponding to each configuration file word segmentation one by one.

[0076] Specifically, each configuration file word segmentation is respectively input into the large language model for processing, and the large language model outputs high-dimensional semantic vectors corresponding to each configuration file word segmentation one by one.

[0077] S220. Obtain configuration key elements based on the high-dimensional semantic vectors and a named entity recognition model.

[0078] S230. Generate corresponding self-check tasks based on the configuration key elements.

[0079] S240. Execute the self-check task to obtain the corresponding self-check result.

[0080] Embodiment III

[0081] A software online environment self-check method provided in Embodiment III of the present application optimizes "obtaining configuration key elements based on the high-dimensional semantic vectors and a named entity recognition model" in Embodiment I; it should be noted that for parts not detailed in this embodiment, the descriptions in other embodiments can be referred to. This method includes:

[0082] S310. Input the obtained online environment configuration file into a large language model for processing to obtain high-dimensional semantic vectors.

[0083] S321, inputting the preset recognition prompt words into the named entity recognition model.

[0084] Among them, the recognition prompt word is used to prompt the named entity recognition model to better focus on the content corresponding to the recognition prompt word, so as to facilitate the named entity recognition model to identify more expected configuration key elements; exemplarily, the preset recognition prompt word is "please extract the file directory, user name, IP address and port configuration in the online environment configuration file"; in this way, it is convenient for the subsequent named entity recognition model to focus more on extracting file directories, user names, IP addresses and port configurations in the process of processing high-dimensional semantic vectors; for this purpose, the preset recognition prompt word can be input into the named entity recognition model.

[0085] S322: Processing the high-dimensional semantic vector based on the named entity recognition model with the recognition prompt word as input to obtain configuration key elements.

[0086] Specifically, each high-dimensional semantic vector is input into a named entity recognition model with a recognition prompt word as input for processing, so that the named entity recognition model outputs one or more corresponding configuration key elements.

[0087] S330: Generate a corresponding self-check task based on the configuration key elements.

[0088] S340: Execute the self-check task to obtain a corresponding self-check result.

[0089] Embodiment 4

[0090] A method for self-checking a software online environment is provided in a fourth embodiment of the present application. The method optimizes the "key configuration elements" in the first embodiment. It should be noted that for the parts not described in detail in the present embodiment, reference may be made to the descriptions of other embodiments. The method includes:

[0091] S410: Input the acquired online environment configuration file into a large language model to obtain a high-dimensional semantic vector.

[0092] S420: Obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model.

[0093] The key configuration elements include: file directory, user name, IP address and port configuration.

[0094] It should be noted that the file directory is used to store configuration files for each online environment, and the port configuration is the configuration parameter information of each port in the online environment.

[0095] S430: Generate a corresponding self-check task based on the configuration key elements.

[0096] S440: Execute the self-check task to obtain a corresponding self-check result.

[0097] Embodiment 5

[0098] A software online environment self-checking method provided in the fifth embodiment of the present application is an extension of the method described in the first embodiment; it should be noted that for the part not described in detail in this embodiment, reference can be made to the description of other embodiments, and reference Figure 2 , the method comprising:

[0099] S510: Input the obtained online environment configuration file into the large language model to obtain a high-dimensional semantic vector.

[0100] S520: Obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model.

[0101] S530: Generate a corresponding self-check task based on the configuration key elements.

[0102] S540: Execute the self-check task to obtain a corresponding self-check result.

[0103] S550: In response to the self-check result indicating that all the self-check tasks have been executed successfully, deploying the software to the online environment corresponding to the online environment configuration file.

[0104] Among them, the self-test result is obtained, and the self-test result can also be judged to determine whether the self-test result means that all self-test tasks have been executed successfully; if it is determined that all self-test tasks have been executed successfully, it means that the online environment is now ready for bank software deployment; at this time, the software can be deployed to the online environment corresponding to the online environment configuration file.

[0105] Specifically, it is determined whether the self-check result indicates that all self-check tasks have been executed successfully. If so, the software is deployed to the online environment corresponding to the online environment configuration file.

[0106] Embodiment 6

[0107] A software online environment self-checking method provided in Example 6 of the present application is an extension of the method described in Example 1; it should be noted that for the parts not described in detail in this embodiment, reference can be made to the descriptions of other embodiments, and reference Figure 3 , the method comprising:

[0108] S610: Input the obtained online environment configuration file into a large language model to obtain a high-dimensional semantic vector.

[0109] S620: Obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model.

[0110] S630: Generate a corresponding self-check task based on the configuration key elements.

[0111] S640: Execute the self-check task to obtain a corresponding self-check result.

[0112] S650: In response to the self-check result indicating that the self-check task is not fully executed, reconfigure the online environment corresponding to the online environment configuration file based on the self-check result to obtain a new online environment.

[0113] Among them, the self-check result is obtained, and the self-check result can also be judged to determine whether the self-check result means that all self-check tasks have been executed successfully; if it is determined that all self-check tasks have not been executed successfully, it means that the online environment is not yet ready for bank software deployment; the self-check result can be further used to determine the specific self-check tasks that have not been executed successfully, and then the configuration key elements corresponding to the self-check tasks that have not been executed successfully can be reconfigured in the online environment. The online environment completes the reconfiguration of the configuration key elements and becomes a new online environment.

[0114] Specifically, determine whether the self-check result shows that all self-check tasks have been executed successfully. If not, determine the self-check tasks that have not been executed successfully based on the self-check result, and then reconfigure the configuration key elements corresponding to the self-check tasks that have not been executed successfully in the online environment to obtain a new online environment.

[0115] S660: Obtain a new online environment configuration file of the new online environment, and obtain a new self-check result based on the new online environment configuration file, until the self-check result indicates that all the self-check tasks have been executed successfully.

[0116] The new online environment has a new online environment configuration file.

[0117] Specifically, based on the new online environment configuration file, steps S610-S650 are executed cyclically until the new self-check result is that all self-check tasks have passed, and then the banking software is deployed to the online environment corresponding to the online environment configuration file.

[0118] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0119] Embodiment 7

[0120] Based on the same inventive concept, this embodiment also provides a software online environment self-checking device for implementing the software online environment self-checking method involved in the above embodiment 1. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more software online environment self-checking device embodiments provided below can refer to the limitations of the software online environment self-checking method above, and will not be repeated here.

[0121] In this embodiment, Figure 4 As shown, a software online environment self-checking device is provided, comprising:

[0122] A vector acquisition module is used to input the acquired online environment configuration file into the large language model to obtain a high-dimensional semantic vector;

[0123] An element acquisition module, used to obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model;

[0124] A task generation module, used to generate corresponding self-check tasks based on the configuration key elements;

[0125] The result generation module is used to execute the self-check task to obtain the corresponding self-check result.

[0126] Embodiment 8

[0127] Based on the same inventive concept, this embodiment also provides a software online environment self-checking device for implementing the software online environment self-checking method involved in the above embodiment 5. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more software online environment self-checking device embodiments provided below can refer to the limitations of the software online environment self-checking method above, and will not be repeated here.

[0128] In this embodiment, Figure 5 As shown, a software online environment self-checking device is provided, comprising:

[0129] A vector acquisition module is used to input the acquired online environment configuration file into the large language model to obtain a high-dimensional semantic vector;

[0130] An element acquisition module, used to obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model;

[0131] A task generation module, used to generate corresponding self-check tasks based on the configuration key elements;

[0132] A result generation module, used for executing the self-check task to obtain the corresponding self-check result;

[0133] The software deployment module is used to deploy the software to the online environment corresponding to the online environment configuration file in response to the self-check result indicating that all the self-check tasks have been executed successfully.

[0134] Embodiment 9

[0135] Based on the same inventive concept, this embodiment also provides a software online environment self-checking device for implementing the software online environment self-checking method involved in the above embodiment 6. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more software online environment self-checking device embodiments provided below can refer to the limitations of the software online environment self-checking method above, and will not be repeated here.

[0136] In this embodiment, Figure 6 As shown, a software online environment self-checking device is provided, comprising:

[0137] A vector acquisition module is used to input the acquired online environment configuration file into the large language model to obtain a high-dimensional semantic vector;

[0138] An element acquisition module, used to obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model;

[0139] A task generation module, used to generate corresponding self-check tasks based on the configuration key elements;

[0140] A result generation module, used for executing the self-check task to obtain the corresponding self-check result;

[0141] An environment configuration module, configured to, in response to the self-check result indicating that the self-check task has not been fully executed, reconfigure the online environment corresponding to the online environment configuration file based on the self-check result to obtain a new online environment;

[0142] The result circulation module is used to obtain a new online environment configuration file of the new online environment, and obtain a new self-check result based on the new online environment configuration file, until the self-check result indicates that all the self-check tasks have been executed successfully.

[0143] Each module in the above-mentioned software online environment self-checking device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0144] It should be noted that, in this embodiment, the obtained online environment configuration file is input into the large language model for processing to obtain a high-dimensional semantic vector; configuration key elements are obtained based on the high-dimensional semantic vector and the named entity recognition model; corresponding self-check tasks are generated based on the configuration key elements; and the self-check tasks are executed to obtain corresponding self-check results; through the above implementation, the online environment configuration file can be processed by the large language model and the named entity recognition model to generate self-check tasks, and there will be no situation where the verification script is manually omitted, which helps to fully improve the verification effect of the software online environment inspection; in addition, the software online environment self-check method is fully automatically executed, which greatly reduces the dependence on manual labor, and does not need to rely on front-end processes / front-end systems, etc., thereby facilitating the full improvement of the verification efficiency of the software online environment inspection.

[0145] In one embodiment, in inputting the obtained online environment configuration file into the large language model for processing to obtain a high-dimensional semantic vector, the vector acquisition module is specifically used to:

[0146] Segmenting the online environment configuration file to obtain configuration file segmentation;

[0147] The configuration file word segmentation is input into a large language model for processing to obtain a high-dimensional semantic vector.

[0148] In one embodiment, in terms of obtaining configuration key elements based on the high-dimensional semantic vector and the named entity recognition model, the element acquisition module is specifically used to:

[0149] Input the preset recognition prompt words into the named entity recognition model;

[0150] The high-dimensional semantic vector is processed based on the named entity recognition model input with the recognition prompt word to obtain configuration key elements.

[0151] Embodiment 10

[0152] In this embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for self-checking a software online environment is implemented.

[0153] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the computer device to which the scheme of the present disclosure is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0154] Embodiment 11

[0155] In this embodiment, a computer readable storage medium is provided. Figure 8 As shown, a computer program is stored thereon, and when the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0156] Embodiment 12

[0157] In this embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.

[0159] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided by the present disclosure can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided by the present disclosure may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited thereto. The processor involved in each embodiment provided by the present disclosure may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited thereto.

[0160] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0161] The above-described embodiments only express several implementation methods of the present disclosure, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present disclosure, and these all belong to the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the attached claims.

Claims

1. A software online environment self-check method, characterized in that: include: Input the obtained online environment configuration file into the large language model to obtain a high-dimensional semantic vector; Obtaining configuration key elements based on the high-dimensional semantic vector and the named entity recognition model; Generate corresponding self-check tasks based on the configuration key elements; Execute the self-check task to obtain a corresponding self-check result.

2. The method according to claim 1, characterized in that: The step of inputting the obtained online environment configuration file into the large language model to obtain a high-dimensional semantic vector includes: Segmenting the online environment configuration file to obtain configuration file segmentation; The configuration file word segmentation is input into a large language model for processing to obtain a high-dimensional semantic vector.

3. The method according to claim 1, characterized in that: The configuration key elements are obtained based on the high-dimensional semantic vector and the named entity recognition model, including: Input the preset recognition prompt words into the named entity recognition model; The high-dimensional semantic vector is processed based on the named entity recognition model input with the recognition prompt word to obtain configuration key elements.

4. The method according to claim 1, characterized in that: The key configuration elements include: file directory, user name, IP address and port configuration.

5. The method according to claim 1, characterized in that Also includes: In response to the self-check result indicating that all the self-check tasks have been executed successfully, the software is deployed to the online environment corresponding to the online environment configuration file.

6. The method according to claim 1, characterized in that Also includes: In response to the self-check result indicating that the self-check task has not been fully executed, reconfiguring the online environment corresponding to the online environment configuration file based on the self-check result to obtain a new online environment; A new online environment configuration file of the new online environment is obtained, and a new self-check result is obtained based on the new online environment configuration file, until the self-check result indicates that all the self-check tasks have been executed successfully.

7. A software online environment self-checking device, characterized in that: The device comprises: A vector acquisition module is used to input the acquired online environment configuration file into the large language model to obtain a high-dimensional semantic vector; An element acquisition module, used to obtain configuration key elements based on the high-dimensional semantic vector and the named entity recognition model; A task generation module, used to generate corresponding self-check tasks based on the configuration key elements; The result generation module is used to execute the self-check task to obtain the corresponding self-check result.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images