System, method and device for realizing intelligent configuration file verification based on large model and rule fusion, processor and readable storage medium
By combining a rule engine with a large-scale intelligent configuration file verification system, the problem of traditional methods failing to detect cross-file logical conflicts is solved, enabling multi-level configuration file verification and improving verification accuracy and intelligence.
Patent Information
- Application Number
- CN202610809362.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-05
- Publication Date
- 2026-08-25
AI Technical Summary
Traditional configuration file verification methods cannot detect logical conflicts or hidden risks between files, leading to system crashes, and lack intelligent support.
By combining a rule engine with a large model, multi-level validation of configuration files is achieved through a configuration loading module, a symbol detection module, a rule validation module, a historical case retrieval module, and a large model analysis module. This includes symbol detection, rule validation, historical case retrieval, and large model analysis, generating structured reports.
It achieves highly accurate and widely applicable configuration file verification, automatically detects potential errors, reduces the risk of human configuration, and improves the intelligent verification capability of configuration changes.
Smart Images
Figure CN122633272A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of intelligent operation and maintenance, and particularly to the field of automated configuration management technology. Specifically, it refers to a system, method, device, processor, and computer-readable storage medium for intelligent configuration file verification based on the fusion of large models and rules. Background Technology
[0002] In traditional operations and maintenance scenarios, configuration file validation relies on manual checks or static script rules. These methods often only detect explicit syntax errors (such as missing parameters or formatting errors) and cannot detect logical conflicts or hidden risks across files. For example, in a multi-module trading system, there is a strict logical dependency between the trading parameter configuration file and the risk control parameter configuration file; inconsistencies in these parameters could lead to system crashes.
[0003] In recent years, with the popularization of automation platforms, enterprise operation and maintenance processes have gradually become automated, but configuration verification still lacks intelligent support. On the other hand, large models (such as Qianwen7B, GPT, etc.) have powerful semantic understanding and knowledge generalization capabilities, which can assist in completing logical reasoning and semantic verification in complex configuration scenarios.
[0004] Therefore, there is an urgent need for an intelligent configuration file verification system that integrates rule engines and large model capabilities, which retains the determinism of structured rules and has the knowledge reasoning and intelligent diagnostic capabilities of large models, thereby enabling cross-system, cross-file, and multi-level configuration verification. Summary of the Invention
[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a system, method, device, processor and computer-readable storage medium for intelligent configuration file verification based on the fusion of large models and rules, which has high verification accuracy, good defect coverage and wide applicability.
[0006] To achieve the above objectives, the present invention provides a system, method, apparatus, processor, and computer-readable storage medium for intelligent configuration file verification based on large model and rule fusion, as follows: This system for intelligent configuration file verification based on the fusion of large models and rules is characterized by comprising a configuration loading module, a symbol detection module, a rule verification module, a historical case retrieval module, a large model analysis module, and a report output module. The configuration loading module is used to automatically load the target configuration file and its associated configuration files, and parse the structure and key-value pairs of the configuration files; The symbol detection module is used to detect the loaded configuration file and identify hidden character errors in the configuration file; The rule verification module reads a predefined rule file and performs single-file constraint rule verification and cross-file logical constraint rule verification. The historical case retrieval module, based on keywords extracted from the historical operation and maintenance work order case library, performs matching retrieval on the current configuration to obtain relevant historical fault case information; The large model analysis module is used to combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts. The report output module is used to summarize the symbol format detection results, step rule verification results, step large model analysis suggestions, and relevant historical cases retrieved, and generate and output a structured verification report.
[0007] Preferably, the symbol detection module detects non-ASCII characters, Chinese parentheses, full-width symbols, incorrect newlines, and mixed indentation to identify hidden character errors in the configuration file.
[0008] Preferably, the single-file constraint rule verification includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verifying whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verifying whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; the cross-file logical constraint rule verification is used to check the parameter references and logical consistency between different configuration files.
[0009] Preferably, the historical operation and maintenance work order case library stores historical work order texts in the form of a file directory, and achieves lightweight search enhancement generation through keyword matching.
[0010] Preferably, the verification report generated by the report output module is in tabular form, including fields for problem status, problem description and repair suggestions, and outputs an exit code representing the overall inspection result.
[0011] The main feature of this method for intelligent configuration file verification based on the fusion of large models and rules is that the method includes the following steps: (1) Load the target configuration file to be verified and its associated configuration files, and parse their structure and key-value pairs; (2) Detect the loaded configuration file and identify hidden character errors in the configuration file; (3) Read the predefined rule file and perform single-file constraint rule verification and cross-file logical constraint rule verification; (4) Based on the keywords extracted from the historical operation and maintenance work order case library, the current configuration is matched and searched to obtain relevant historical fault case information; (5) Combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts; (6) Summarize the symbol format detection results, rule verification results, large model analysis suggestions and relevant historical cases retrieved, generate a structured verification report and output it.
[0012] Preferably, the single-file constraint rule verification in step (3) includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verifying whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verifying whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; the cross-file logical constraint rule verification is used to check the parameter references and logical consistency between different configuration files.
[0013] The device for intelligent configuration file verification based on the fusion of large models and rules is characterized in that the device includes: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for intelligent configuration file verification based on the fusion of large models and rules.
[0014] The processor for intelligent configuration file verification based on the fusion of large models and rules is characterized in that the processor is configured to execute computer-executable instructions, and when the computer-executable instructions are executed by the processor, the various steps of the above-mentioned method for intelligent configuration file verification based on the fusion of large models and rules are implemented.
[0015] The main feature of this computer-readable storage medium is that it stores a computer program thereon, which can be executed by a processor to implement the various steps of the above-described method for intelligent configuration file verification based on the fusion of large models and rules.
[0016] This invention employs a system, method, apparatus, processor, and computer-readable storage medium for intelligent configuration file verification based on a large model and rule fusion. Combining a rule engine, historical case knowledge base, and large language model (LLM), it achieves syntactic, logical, and cross-system consistency verification of multi-source configuration files. The system automatically detects potential errors in configuration files through four stages: symbol detection, rule parsing, semantic reasoning, and fault precedent retrieval. These errors include format symbol errors, logical conflicts, cross-system parameter inconsistencies, and unreasonable resource configurations. This invention can be widely applied in scenarios such as enterprise automated operation and maintenance, securities trading systems, and cloud-native cluster configuration management, effectively reducing the risk of human configuration and improving the intelligent verification capability of configuration changes. Attached Figure Description
[0017] Figure 1 This is a schematic diagram of the system for intelligent configuration file verification based on the fusion of large models and rules according to the present invention. Detailed Implementation
[0018] To more clearly describe the technical content of the present invention, the following description is provided in conjunction with specific embodiments.
[0019] The present invention discloses a system for intelligent configuration file verification based on the fusion of large models and rules, comprising a configuration loading module, a symbol detection module, a rule verification module, a historical case retrieval module, a large model analysis module, and a report output module. The configuration loading module is used to automatically load the target configuration file and its associated configuration files, and parse the structure and key-value pairs of the configuration files; The symbol detection module is used to detect the loaded configuration file and identify hidden character errors in the configuration file; The rule verification module reads a predefined rule file and performs single-file constraint rule verification and cross-file logical constraint rule verification. The historical case retrieval module, based on keywords extracted from the historical operation and maintenance work order case library, performs matching retrieval on the current configuration to obtain relevant historical fault case information; The large model analysis module is used to combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts. The report output module is used to summarize the symbol format detection results, step rule verification results, step large model analysis suggestions, and relevant historical cases retrieved, and generate and output a structured verification report.
[0020] In a preferred embodiment of the present invention, the symbol detection module detects non-ASCII characters, Chinese parentheses, full-width symbols, incorrect newlines, and mixed indentation to identify hidden character errors in the configuration file.
[0021] In a preferred embodiment of the present invention, the single-file constraint rule verification includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verifying whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verifying whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; the cross-file logical constraint rule verification is used to check the parameter references and logical consistency between different configuration files.
[0022] In a preferred embodiment of the present invention, the historical maintenance work order case library stores historical work order texts in the form of a file directory, and achieves lightweight retrieval enhancement generation through keyword matching.
[0023] In a preferred embodiment of the present invention, the verification report generated by the report output module is in tabular form, including fields for problem status, problem description and repair suggestion, and outputs an exit code representing the overall inspection result.
[0024] The present invention discloses a method for intelligent configuration file verification based on the fusion of large models and rules, wherein the method includes the following steps: (1) Load the target configuration file to be verified and its associated configuration files, and parse their structure and key-value pairs; (2) Detect the loaded configuration file and identify hidden character errors in the configuration file; (3) Read the predefined rule file and perform single-file constraint rule verification and cross-file logical constraint rule verification; (4) Based on the keywords extracted from the historical operation and maintenance work order case library, the current configuration is matched and searched to obtain relevant historical fault case information; (5) Combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts; (6) Summarize the symbol format detection results, rule verification results, large model analysis suggestions and relevant historical cases retrieved, generate a structured verification report and output it.
[0025] As a preferred embodiment of the present invention, the single-file constraint rule verification in step (3) includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verifying whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verifying whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; the cross-file logical constraint rule verification is used to check the parameter references and logical consistency between different configuration files.
[0026] The present invention relates to an apparatus for intelligent configuration file verification based on the fusion of large models and rules, wherein the apparatus comprises: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the various steps of the above-described method for intelligent configuration file verification based on the fusion of large models and rules.
[0027] The main feature of the processor for intelligent configuration file verification based on the fusion of large models and rules of the present invention is that the processor is configured to execute computer-executable instructions, and when the computer-executable instructions are executed by the processor, the various steps of the above-mentioned method for intelligent configuration file verification based on the fusion of large models and rules are implemented.
[0028] The computer-readable storage medium of the present invention stores a computer program thereon, which can be executed by a processor to implement the various steps of the above-described method for intelligent configuration file verification based on the fusion of large models and rules.
[0029] The purpose of this invention is to provide an intelligent configuration file verification system based on the fusion of large models and rules, which can automatically identify syntax errors and non-standard symbols in configuration files; verify the logical consistency between multiple files and multiple systems; perform semantic completion and intelligent diagnosis using historical work orders and large model knowledge; and seamlessly integrate with the Blue Whale platform to achieve automated inspection and visual report output.
[0030] The configuration file verification system based on the fusion of large models and rules of the present invention includes a configuration loading module, a symbol detection module, a rule verification module, a historical case retrieval module, a large model analysis module, and a report output module.
[0031] The symbol detection module is used to detect non-ASCII symbols, Chinese parentheses, full-width punctuation marks, incorrect newline characters, and spaces mixed together.
[0032] The rule validation module supports single-file rules and cross-file logical rules, and the rules are defined in YAML format.
[0033] The historical case retrieval module implements lightweight RAG enhancement based on keyword matching.
[0034] The large model analysis module calls Qianwen 7B or other large language model interfaces to perform semantic analysis and generate repair suggestions on the configuration file.
[0035] This system can be deployed on an automation platform, where it can be executed automatically through task nodes and output result tables.
[0036] In a specific embodiment of the present invention, the technical solution of the present invention includes the following steps: Configuration loading module: Automatically loads the target configuration file and its associated files, and parses the structure and key-value pairs.
[0037] Symbol detection module: Detects non-ASCII characters, Chinese parentheses, full-width symbols, incorrect newlines, mixed indentation, etc.
[0038] Rule validation module: Reads single-file and cross-file constraint rules defined in the rules.yaml file, including: The number of parameters must match (e.g., exec_server_num must match the number of services). ID format verification; Cross-file logical references (e.g., execNum in resume.sh must exist in exec.properties).
[0039] Historical Case Retrieval Module: Extracts keyword-matching cases from the historical incidents / directory to achieve lightweight RAG enhancement.
[0040] Large Model Analysis Module: Calls the Qianwen 7B interface to perform semantic reasoning on the configuration file and outputs optimization suggestions and potential risks.
[0041] Report output module: Generates tabular reports (including status, description, and recommendations) and displays them on the front end of the automation platform.
[0042] The system consists of the following parts: Front-end automation interface layer: receives tasks and displays inspection results; Rule engine layer: Parses rules.yaml and prompts.yaml; Analysis core modules: symbol detection + rule validation + LLM invocation; Knowledge Enhancement Module (RAG): Retrieves historical work orders and enhances the context; Results output module: Generates a visual report and outputs the exit code.
[0043] The following example uses a trading system configuration file: exec.properties: Defines the execution node and strategy type; strategy.properties: Defines the policy server ID; resume.sh: contains the execNum parameter from the automatic recovery script.
[0044] When executing `python config_checker.py --conf exec.properties --rulesrules.yaml --incidents incidents / `, The system will execute: Detects Chinese parentheses and Windows line breaks; Check that the number of servers matches their serial numbers; Verify that execNum in resume.sh exists in the main configuration; Call the Qianwen 7B interface to output an intelligent optimization report; Output the results table and match historical cases.
[0045] The core value of this invention lies in not generating or modifying any configuration, but focusing on performing multi-level and multi-dimensional static diagnosis of existing configurations and outputting risk diagnosis reports for human decision-making.
[0046] This invention explicitly includes specific detection at the format level, such as non-ASCII characters, Chinese parentheses, full-width symbols, and incorrect newline characters. These "hidden character errors" do not affect file syntax parsing but can cause device execution abnormalities, representing a common pain point in manual configuration entry during actual operation and maintenance scenarios. The parsers for both comparison files only focus on structural matching of views and syntax, without covering character set-level detection.
[0047] This invention introduces a retrieval enhancement module based on historical maintenance work order cases as a knowledge base. It utilizes keyword matching to retrieve experience from real historical fault cases, enabling the large model to perform analogical diagnosis of configuration risks by combining the enterprise's historical experience. This is an innovative mechanism that integrates structured enterprise private maintenance knowledge into intelligent analysis.
[0048] This invention's rule engine can verify parameter consistency across files (such as the matching relationships between port numbers, IP addresses, and parameter references across multiple configuration files), going beyond the scope of single-file syntax verification. The processing objects for both comparison files are single configuration files, and cross-file association constraint verification is not involved.
[0049] This invention is a "diagnostic auditing" system. Combining a production system with a scheduling system does not logically lead to the design concept of an auditing system.
[0050] In this invention, the rule engine and the large model are parallel, independently operating collaborative core units, each undertaking different types of verification tasks—the rule engine is responsible for deterministic rule verification, and the large model is responsible for semantic reasoning and risk prediction. The outputs of both constitute the final diagnostic report, reflecting the architectural idea of "complementary enhancement" rather than "master-slave verification".
[0051] The present invention has the following technical effects: (1) Collaborative improvement of verification accuracy The high-precision output of the rule engine can provide a structured list of known errors for large models, enabling them to focus on semantic-level issues that the rule engine cannot cover. This avoids redundant analysis and potential misjudgments within the constraints of existing rules. The overall accuracy of the combined approach is significantly better than the sum of the two.
[0052] (2) The “experience analogy” effect brought about by the introduction of historical case RAG By semantically associating historical work orders with the current configuration, the system can discover the similarity between the current configuration and known historical failure modes, enabling diagnostic reasoning that "failures have occurred under this type of configuration, and the current configuration carries a similar risk." This predictive diagnostic capability based on historical experience is something that pure rule engines and large models without historical knowledge enhancement cannot achieve, and it is a new capability brought about by this integrated architecture.
[0053] For example, during configuration verification after an upgrade of a trading strategy system, this system, through historical work order retrieval, discovered that the current configuration was highly similar to the faulty configuration pattern that caused the trading failure three months prior. This successfully alerted the system to the potential risk, while traditional rule engines and general-purpose models failed to detect the issue. This successfully prevented a significant failure from occurring.
[0054] (3) Defect coverage effect of multi-level verification This layered, progressive verification architecture, from character format layer (symbol detection) → single-file syntax logic layer (rule engine) → cross-file constraint layer (rule engine) → semantic risk layer (large model + RAG), enables the system to detect all defects in format, logic, and semantics in a single run. This invention's integrated architecture delivers unexpected overall benefits in terms of practicality.
[0055] For the specific implementation scheme of this embodiment, please refer to the relevant descriptions in the above embodiments, which will not be repeated here.
[0056] It is understood that the same or similar parts in the above embodiments can be referred to each other, and the contents not described in detail in some embodiments can be referred to the same or similar contents in other embodiments.
[0057] It should be noted that in the description of this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Furthermore, in the description of this invention, unless otherwise stated, "a plurality of" means at least two.
[0058] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.
[0059] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution device. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0060] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The corresponding program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.
[0061] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0062] The storage media mentioned above can be read-only memory, disk, or optical disk, etc.
[0063] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.
[0064] This invention employs a system, method, apparatus, processor, and computer-readable storage medium for intelligent configuration file verification based on a large model and rule fusion. Combining a rule engine, historical case knowledge base, and large language model (LLM), it achieves syntactic, logical, and cross-system consistency verification of multi-source configuration files. The system automatically detects potential errors in configuration files through four stages: symbol detection, rule parsing, semantic reasoning, and fault precedent retrieval. These errors include format symbol errors, logical conflicts, cross-system parameter inconsistencies, and unreasonable resource configurations. This invention can be widely applied in scenarios such as enterprise automated operation and maintenance, securities trading systems, and cloud-native cluster configuration management, effectively reducing the risk of human configuration and improving the intelligent verification capability of configuration changes.
[0065] In this specification, the invention has been described with reference to specific embodiments thereof. However, it will be apparent that various modifications and variations can be made without departing from the spirit and scope of the invention. Therefore, the specification and drawings should be considered illustrative rather than restrictive.
Claims
1. A system for intelligent configuration file verification based on the fusion of large models and rules, characterized in that, The system includes a configuration loading module, a symbol detection module, a rule validation module, a historical case retrieval module, a large model analysis module, and a report output module. The configuration loading module is used to automatically load the target configuration file and its associated configuration files, and parse the structure and key-value pairs of the configuration files; The symbol detection module is used to detect the loaded configuration file and identify hidden character errors in the configuration file; The rule verification module reads a predefined rule file and performs single-file constraint rule verification and cross-file logical constraint rule verification. The historical case retrieval module, based on keywords extracted from the historical operation and maintenance work order case library, performs matching retrieval on the current configuration to obtain relevant historical fault case information; The large model analysis module is used to combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts. The report output module is used to summarize the symbol format detection results, step rule verification results, step large model analysis suggestions, and relevant historical cases retrieved, and generate and output a structured verification report.
2. The system for intelligent configuration file verification based on the fusion of large models and rules as described in claim 1, characterized in that, The symbol detection module detects non-ASCII characters, Chinese parentheses, full-width symbols, incorrect newlines, and mixed indentation to identify hidden character errors in the configuration file.
3. The system for intelligent configuration file verification based on the fusion of large models and rules as described in claim 1, characterized in that, The single-file constraint rule verification includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verification of whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verification of whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; Cross-file logical constraint rule validation is used to check the consistency of parameter references and logic between different configuration files.
4. The system for intelligent configuration file verification based on the fusion of large models and rules as described in claim 1, characterized in that, The historical operation and maintenance work order case library stores historical work order texts in the form of a file directory, and achieves lightweight search enhancement generation through keyword matching.
5. The system for intelligent configuration file verification based on the fusion of large models and rules as described in claim 1, characterized in that, The verification report generated by the report output module is in tabular form, containing fields for problem status, problem description, and repair suggestions, and outputs an exit code representing the overall inspection result.
6. A method for intelligent configuration file verification based on the fusion of large models and rules in the system described in claim 1, characterized in that, The method includes the following steps: (1) Load the target configuration file to be verified and its associated configuration files, and parse their structure and key-value pairs; (2) Detect the loaded configuration file and identify hidden character errors in the configuration file; (3) Read the predefined rule file and perform single-file constraint rule verification and cross-file logical constraint rule verification; (4) Based on the keywords extracted from the historical operation and maintenance work order case library, the current configuration is matched and searched to obtain relevant historical fault case information; (5) Combine the processed configuration information, verification results and retrieved historical case information into prompt words, call the large language model interface to perform semantic reasoning and analysis, and generate optimization suggestions for configuration semantic risks and potential logical conflicts; (6) Summarize the symbol format detection results, rule verification results, large model analysis suggestions and relevant historical cases retrieved, generate a structured verification report and output it.
7. The method for intelligent configuration file verification based on the fusion of large models and rules as described in claim 6, characterized in that, The single-file constraint rule verification in step (3) includes verification of the parameter value range and verification of the identifier ID format; the cross-file logical constraint rule verification includes verifying whether the number of parameters defined in the first configuration file is consistent with the number of services actually listed in the second configuration file, and verifying whether the parameter values referenced in the third configuration file exist in the definition of the first configuration file; Cross-file logical constraint rule validation is used to check the consistency of parameter references and logic between different configuration files.
8. A device for intelligent configuration file verification based on the fusion of large models and rules, characterized in that, The device includes: A processor is configured to execute computer-executable instructions; The memory stores one or more computer-executable instructions, which, when executed by the processor, implement the steps of the method for intelligent configuration file verification based on the fusion of large models and rules as described in any one of claims 6 to 7.
9. A processor for intelligent configuration file verification based on the fusion of large models and rules, characterized in that, The processor is configured to execute computer-executable instructions, which, when executed by the processor, implement the steps of the method for intelligent configuration file verification based on the fusion of large models and rules as described in any one of claims 6 to 7.
10. A computer-readable storage medium, characterized in that, It stores a computer program that can be executed by a processor to implement the various steps of the method for intelligent configuration file verification based on the fusion of large models and rules, as described in any one of claims 6 to 7.