Train control data auditing method and device and storage medium

Abstract

The invention provides a train control data auditing method and device and a storage medium. The method comprises the steps that data related to a train control data auditing rule is converted into structured data; based on a pre-trained generative artificial intelligence model, generating a train control data auditing rule code according to the structured data; the to-be-audited train control data is audited according to the train control data auditing rule code, on one hand, the generation efficiency and the standardization degree of the train control data auditing rule code are improved by combining an artificial intelligence model, and the auditing efficiency of the train control data is effectively improved; and on the other hand, the generation capability and reliability of the artificial intelligence model are considered, the use threshold is reduced, the generation creation capability of the artificial intelligence model is reserved, the auditing rule code is ensured to meet the reliability requirement in the railway track field, the development period is effectively shortened, and the development cost and the labor cost are reduced.

Description

Technical Field

[0001] This article relates to data processing technology, particularly a method, device, and storage medium for auditing train control data. Background Technology

[0002] Train control data is a crucial foundation for the reliable operation of the train control system and a key factor in ensuring train operation safety. The accuracy and standardization of train control data are the cornerstone of safe train operation. However, in practical engineering applications, the generation and review process of train control data still faces many challenges, mainly in the following aspects: 1) Low efficiency of manual review: Traditional train control data review relies on manual labor, requiring repeated comparisons and verifications of the data's logical relationships, format specifications, and numerical rationality. This process is not only time-consuming and labor-intensive, requiring highly experienced reviewers, but also highly susceptible to human error due to fatigue or negligence, making it difficult to meet the needs of large-scale, high-frequency data verification. 2) Insufficient standardization: Existing train control data management specifications do not fully cover various special scenarios and boundary conditions, and different design institutes have differences in data formats and naming rules, lacking a unified standard. This results in strong data heterogeneity, significantly increasing the complexity of cross-unit and cross-line data integration and review. Summary of the Invention

[0003] This application provides a method, device, and storage medium for auditing train control data, which can improve audit efficiency and the standardization of train control data audit rule codes.

[0004] Firstly, embodiments of this application provide a method for auditing train control data, including: The data related to the audit rules for train control data is converted into structured data. The fields of the structured data include: the name of the audit rule, the data involved in the audit rule and its data source information, and the audit logic. Based on a pre-trained generative artificial intelligence model, train control data audit rule codes are generated from structured data; The train control data to be audited is audited according to the train control data audit rule code.

[0005] In one possible implementation, a pre-trained generative artificial intelligence model is used to generate train control data audit rule codes based on structured data, including: Based on a pre-trained generative artificial intelligence model, the system identifies prompts entered by the user. If the user indicates a code generation operation, the system determines code constraints based on the prompts entered by the user. Based on the code constraints and structured data, the system generates train control data audit rule codes.

[0006] In one possible implementation, the code constraints include at least one of the following: Each review rule corresponds to a code module; The code is written in Python. The entry function name and input parameter types of the code are consistent, and the input parameter types are consistent with the data data source data involved in the relevant audit rules; The output information of the code is consistent; If an error is detected in the train control data to be audited during code execution, the error message is recorded and the system continues to check other parts of the train control data to be audited.

[0007] One possible implementation also includes: Store the column control data audit rule code and its attribute information corresponding to each audit rule. The attribute information of the column control data audit rule code includes at least one of the following: name, number, and version information.

[0008] In one possible implementation, the train control data to be audited is audited according to the train control data audit rule code, including: Based on a pre-trained generative artificial intelligence model, the system identifies prompts entered by the user. If the user indicates an audit operation, the system determines the attribute information of the target train control data audit rule code and the train control data to be audited based on the prompts. Based on the attribute information of the target train control data audit rule code, the system retrieves the pre-stored target train control data audit rule code, audits the train control data to be audited using the target train control data audit rule code, and outputs the audit result.

[0009] One possible implementation also includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts entered by the user. If the user indicates a query operation, the system determines the attribute information of the train control data audit rule code to be queried based on the prompts. Based on the attribute information of the train control data audit rule code to be queried, the system queries the pre-stored train control data audit rule code and outputs the query results.

[0010] One possible implementation also includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts input by the user. If the user indicates a modification operation, the system determines the attribute information and modification content of the train control data audit rule code to be modified based on the prompts. Based on the attribute information of the train control data audit rule code to be modified, the system retrieves the pre-stored train control data audit rule code to be modified, modifies the train control data audit rule code to be modified according to the modification content, and stores the modified train control data audit rule code and its version information.

[0011] In one possible implementation, the data related to the train control data audit rules includes: train control data audit guidelines.

[0012] Secondly, embodiments of this application also provide an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements any of the methods provided in the first aspect.

[0013] Thirdly, embodiments of this application also provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the methods provided in the first aspect.

[0014] The train control data auditing method, device, and storage medium provided in this application convert data related to train control data auditing rules into structured data. The structured data fields include: the name of the auditing rule, the data involved in the auditing rule and its data source information, and the auditing logic. Based on a pre-trained generative artificial intelligence model, train control data auditing rule codes are generated from the structured data. The train control data to be audited is then audited according to these auditing rule codes. On the one hand, by combining the artificial intelligence model, the generation efficiency and standardization of train control data auditing rule codes are improved, effectively enhancing the auditing efficiency of train control data. On the other hand, the generative capability and reliability of the artificial intelligence model are considered, lowering the usage threshold. While retaining the generative creativity of the artificial intelligence model, it ensures that the auditing rule codes meet the reliability requirements of the railway track field, effectively shortening the development cycle and reducing development and labor costs.

[0015] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the application. Other advantages of this application can be realized and obtained by means of the embodiments described in the description and the accompanying drawings. Attached Figure Description

[0016] The accompanying drawings are used to provide an understanding of the technical solutions of this application and constitute a part of the specification. They are used together with the embodiments of this application to explain the technical solutions of this application and do not constitute a limitation on the technical solutions of this application.

[0017] Figure 1 This is a flowchart illustrating a method for auditing train control data provided in an embodiment of this application. Detailed Implementation

[0018] This application describes several embodiments, but these descriptions are exemplary and not limiting, and it will be apparent to those skilled in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment may be used in combination with, or may replace, any feature or element of any other embodiment.

[0019] This application includes and contemplates combinations of features and elements known to those skilled in the art. The embodiments, features, and elements disclosed in this application can also be combined with any conventional features or elements to form unique inventive solutions. Any feature or element of any embodiment can also be combined with features or elements from other inventive solutions to form another unique inventive solution. Therefore, it should be understood that any feature shown and / or discussed in this application can be implemented individually or in any suitable combination. Therefore, the embodiments are not limited except by the limitations imposed by the appended claims and their equivalents. Furthermore, various modifications and changes can be made within the scope of the appended claims.

[0020] Furthermore, in describing representative embodiments, the specification may have presented methods and / or processes as a specific sequence of steps. However, the method or process should not be limited to a specific order of steps to the extent that it does not depend on this specific order. As will be understood by those skilled in the art, other sequences of steps are also possible. Therefore, the specific order of steps set forth in the specification should not be construed as a limitation of the claims. Moreover, the claims relating to the method and / or process should not be limited to the steps performed in the order written, and those skilled in the art will readily understand that these orders can be varied and still remain within the spirit and scope of the embodiments of this application.

[0021] To address the problems existing in current technologies, the railway industry urgently needs an efficient and intelligent method for train control data verification. Currently, there have been attempts to manually construct verification code based on train control data verification specifications, but this approach has the following drawbacks: 1) High development cost: Verification rules need to be coded line by line by developers, relying heavily on manpower; 2) Long development cycle: Developers have limited understanding of the technical details and business background of the verification specifications, often requiring frequent communication with design reviewers to confirm requirements. This long information transmission chain prolongs the cycle from rule formulation to implementation, resulting in untimely responses; 3) High maintenance difficulty: Current train control data verification specifications involve more than ten related data tables and hundreds of verification rules, with complex logic and high coupling. Once the verification specifications change, a large amount of verification code often needs to be refactored, leading to difficulties in version iteration, increased testing costs, and a large overall maintenance workload.

[0022] If structured audit specifications can be automatically converted into executable verification logic, it will not only closely align with the actual needs of design reviewers, significantly improving rule conversion efficiency and verification accuracy, but also enable rapid iteration and dynamic deployment of verification rules. If intelligent methods can be used to reduce reliance on manual coding, it will effectively reduce human intervention and communication costs, comprehensively improve the automation and standardization of train control data verification, and provide a solid and reliable technical guarantee for the safe and efficient operation of railway transportation. Based on this, this application provides a method for auditing train control data, such as... Figure 1 As shown, the method includes: S101. Convert the data related to the train control data audit rules into structured data.

[0023] The fields in the structured data include: the name of the audit rule, the data involved in the audit rule and its data source information, and the audit logic.

[0024] Specifically, this could involve converting data related to train control data audit rules, described in natural language, into structured data that is easily understood by generative artificial intelligence models.

[0025] Optionally, data related to the train control data audit rules includes: train control data audit guidelines.

[0026] For example, Table 1 shows data related to train control data audit rules provided in this application. In the example shown in Table 1, the data related to train control data audit rules uses natural language, which is not conducive to the understanding and processing of generative artificial intelligence models. Directly using data described in natural language as input for generative artificial intelligence models to generate rule codes will lead to the following problems: 1) unclear data positioning; 2) insufficient understanding of specific terms; 3) poor standardization of the generated data verification rule codes. Therefore, this application has standardized the data format and adopted a structured data format to convert the data related to train control data audit rules into structured data as shown in Table 2, so that the generative artificial intelligence model can clearly define the data source information and audit logic involved in each rule, improve the understanding ability of the generative artificial intelligence model, and improve the generation efficiency of audit rule codes.

[0027] Table 1. Data related to train control data audit rules described using natural language. Table 2 Structured Data In the structured data shown in Table 2, the rule name pairs represent the names of the audit rules. The data source indicates the data source information involved in the audit rule; data sources 1-3 represent different data source information, and the detection rule represents the audit logic. It should be noted that Table 2 is only an example and does not impose specific limitations. The fields in the structured data can be set according to actual needs.

[0028] Alternatively, for ease of reading and comparison, the structured data can be presented in tabular form as shown in Table 3: Table 3. Tables corresponding to structured data S102. Based on a pre-trained generative artificial intelligence model, generate train control data audit rule codes according to structured data.

[0029] Pre-trained generative AI models can be Deepseek, ChatGPT, etc. This model integrates a large language model, enabling it to recognize user-input prompts and acquire expertise in the railway track domain.

[0030] Specifically, the pre-trained generative artificial intelligence model deeply integrates professional knowledge in the railway track field and can generate train control data audit rule codes by combining structured data transformed from data related to train control data audit rules input by users.

[0031] In one possible implementation, train control data audit rule codes are generated based on structured data using a pre-trained generative artificial intelligence model. This includes: identifying prompts input by the user based on the pre-trained generative artificial intelligence model; if it is determined that the user has instructed a code generation operation, determining code constraints based on the prompts input by the user; and generating train control data audit rule codes based on the code constraints and structured data.

[0032] For example, a user can input structured data derived from data related to train control data audit rules and prompts containing the user's intent into a pre-trained generative AI model. This allows the pre-trained generative AI model to identify the user's intent by analyzing the prompts and then execute the user's instructions based on the structured data.

[0033] For example, a user uploads structured data, converted from data related to train control data audit rules, as an attachment to a pre-trained generative AI model, and inputs "Please generate train control data audit rule codes corresponding to each audit rule based on the attachment content" into the pre-trained generative AI model. The pre-trained generative AI model recognizes the user's prompt and determines that the user needs to generate train control data audit rule codes based on the uploaded structured data, and then executes the operation.

[0034] This method provides the data source information that each rule needs to detect in a structured form to the generative artificial intelligence model, ensuring that it can correctly understand the data format and content; and clearly expresses the industry-specific review logic of each rule, with the content focusing on the core scenario of railway track control, ensuring that it accurately captures the review standards of train control data.

[0035] Optionally, the code constraints include at least one of the following: Each review rule corresponds to a code module; The code is written in Python. The entry function name and input parameter types of the code are consistent, and the input parameter types are consistent with the data data source data involved in the relevant audit rules; The output information of the code is consistent; If an error is detected in the train control data to be audited during code execution, the error message is recorded and the system continues to check other parts of the train control data to be audited.

[0036] For example, the code outputs uniform information, specifically including `is_pass` and `msg`. `is_pass` is an integer, where 0 indicates failure and 1 indicates success; `msg` is a string representing relevant error messages. During code execution, when an error is detected in the train control data to be audited, the audit does not terminate immediately. Instead, the error information is recorded, and the audit continues on other parts of the train control data to be audited.

[0037] This method generates train control data audit rule code stored as Python modules, with each rule corresponding to an independent module file. Using Python, different rule-related modules can be dynamically loaded via import, and hot updates and execution of audit logic can be achieved, adapting to the high-frequency iteration requirements of railway track control rules.

[0038] By designing code constraints and implementing dedicated domain-specific Prompt templates, AI models are guided to generate syntactically correct, logically rigorous, and highly readable verification code. Combining code generation with modification feedback ensures that the generated code not only conforms to verification rules but also records detailed violation locations, data context, and modification suggestions, providing a clear basis for correcting train control data files.

[0039] S103. Audit the train control data to be audited according to the train control data audit rule code.

[0040] Specifically, different aspects of the audit can be performed on the train control data to be audited using the corresponding train control data audit rule codes for different rules.

[0041] Optionally, the method further includes storing the column control data audit rule code and its attribute information corresponding to each audit rule. The attribute information of the column control data audit rule code includes at least one of the following: name, number, and version information.

[0042] This method enables version management of the audit rule code for train control data.

[0043] In one possible implementation, the auditing of the train control data to be audited based on the train control data audit rule code includes: identifying prompt words input by the user based on a pre-trained generative artificial intelligence model; if it is determined that the user has indicated an audit operation, determining the attribute information of the target train control data audit rule code and the train control data to be audited based on the prompt words; obtaining the pre-stored target train control data audit rule code based on the attribute information of the target train control data audit rule code; auditing the train control data to be audited using the target train control data audit rule code; and outputting the audit result.

[0044] This method enables the execution of corresponding column control data audit rule codes based on user-input prompts, and completes the audit according to predetermined audit logic. The audit process is fully automated and supports complex logic audits across tables and fields.

[0045] Optionally, the method further includes: identifying prompt words input by the user based on a pre-trained generative artificial intelligence model; if it is determined that the user indicates a query operation, determining the attribute information of the train control data audit rule code to be queried based on the prompt words; querying the pre-stored train control data audit rule code based on the attribute information of the train control data audit rule code to be queried and outputting the query result.

[0046] This method enables the querying of corresponding train control data audit rule codes based on user-input prompts.

[0047] Optionally, the method further includes: based on a pre-trained generative artificial intelligence model, identifying prompt words input by the user; if it is determined that the user indicates a modification operation, determining the attribute information and modification content of the train control data audit rule code to be modified according to the prompt words; obtaining the pre-stored train control data audit rule code to be modified according to the attribute information of the train control data audit rule code to be modified; modifying the train control data audit rule code to be modified according to the modification content; and storing the modified train control data audit rule code and the code version information.

[0048] Optionally, the modification can be specific content that needs to be changed, such as changing the content of data source 1 in rule "r1_2" from "transponder location table || downstream forward || sequence number, station name" to "transponder location table || downstream forward || reverse number, station name". The modification can also be indicative content, such as modifying rule r1_2 according to the latest published train control data audit guidelines.

[0049] This method combines generative artificial intelligence models with railway industry knowledge to automatically update the corresponding train control verification rule codes based on user-input prompts, effectively reducing the maintenance cost of train control verification rule codes while ensuring user control over the verification rules.

[0050] Specifically, pre-trained generative AI models determine the type of operation instructed by the user by matching the prompts entered by the user with predefined intent types, ensuring the accuracy and robustness of the recognition results. By recognizing different intents and executing different operations, it can efficiently meet the diverse needs of engineers in the development, maintenance, and application of train control data verification rules.

[0051] The train control data auditing method provided in this application converts data related to train control data auditing rules into structured data. The structured data fields include: the name of the auditing rule, the data involved in the auditing rule and its data source information, and the auditing logic. Based on a pre-trained generative artificial intelligence model, train control data auditing rule codes are generated from the structured data. The train control data to be audited is then audited according to these auditing rule codes. This achieves an efficient and intelligent train control data auditing method. On the one hand, by combining artificial intelligence models, it improves the generation efficiency and standardization of train control data auditing rule codes, effectively enhancing the auditing efficiency of train control data. On the other hand, it not only considers the generation capability and reliability of artificial intelligence models, lowering the usage threshold, but also ensures that the auditing rule codes meet the reliability requirements of the railway track field while retaining the generative creativity of artificial intelligence models, effectively shortening the development cycle and reducing development and labor costs.

[0052] This application also provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the methods provided in the above-described method embodiments.

[0053] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the methods provided in the above-described method embodiments.

[0054] It will be understood by those skilled in the art that all or some of the steps, systems, or apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term "computer storage medium" includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0055] In the description of this specification, the 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 this application. 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. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0056] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for auditing train control data, characterized in that, include: The data related to the audit rules for train control data is converted into structured data. The fields of the structured data include: the name of the audit rule, the data involved in the audit rule and its data source information, and the audit logic. Based on a pre-trained generative artificial intelligence model, train control data audit rule codes are generated according to the structured data; The train control data to be audited is audited according to the train control data audit rule code.

2. The method according to claim 1, characterized in that, The process of generating train control data audit rule codes based on the pre-trained generative artificial intelligence model and the structured data includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts input by the user. If it is determined that the user has indicated a code generation operation, the system determines code constraints based on the prompts input by the user. Based on the code constraints and the structured data, the system generates the train control data audit rule code.

3. The method according to claim 2, characterized in that, The code constraints include at least one of the following: Each review rule corresponds to a code module; The code is written in Python. The entry function name and input parameter types of the code are consistent, and the input parameter types are consistent with the data data source data involved in the relevant audit rules; The output information of the code is consistent; If an error is detected in the train control data to be audited during code execution, the error message is recorded and the system continues to check other parts of the train control data to be audited.

4. The method according to claim 1, characterized in that, The method further includes: The system stores the column control data audit rule code and its attribute information corresponding to each audit rule. The attribute information of the column control data audit rule code includes at least one of the following: name, number, and version information.

5. The method according to claim 4, characterized in that, The step of auditing the train control data to be audited according to the train control data audit rule code includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts input by the user. If the user indicates an audit operation, the system determines the attribute information of the target train control data audit rule code and the train control data to be audited based on the prompts. Based on the attribute information of the target train control data audit rule code, the system retrieves the pre-stored target train control data audit rule code, audits the train control data to be audited using the target train control data audit rule code, and outputs the audit result.

6. The method according to claim 4, characterized in that, The method further includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts entered by the user. If the user indicates a query operation, the system determines the attribute information of the train control data audit rule code to be queried based on the prompts. Based on the attribute information of the train control data audit rule code to be queried, the system queries the pre-stored train control data audit rule code and outputs the query results.

7. The method according to claim 4, characterized in that, The method further includes: Based on a pre-trained generative artificial intelligence model, the system identifies prompts input by the user. If the user indicates a modification operation, the system determines the attribute information and modification content of the train control data audit rule code to be modified based on the prompts. Based on the attribute information of the train control data audit rule code to be modified, the system retrieves the pre-stored train control data audit rule code to be modified, modifies the train control data audit rule code to be modified according to the modification content, and stores the modified train control data audit rule code and its version information.

8. The method according to claim 1, characterized in that, The data related to the train control data audit rules includes: train control data audit guidelines.

9. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.

Images