Calibration method, system and equipment for nuclear power design file and medium
By obtaining the metadata of the nuclear power design files, static rules and dynamic technical inspections are carried out, and hierarchical warnings are performed in combination with the verification model, the problem of inefficient manual verification of nuclear power design files is solved, and efficient and automated document review is achieved.
Patent Information
- Application Number
- CN202510454571.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-11
- Publication Date
- 2025-07-25
AI Technical Summary
The verification of nuclear power design files in the prior art relies on manual differences comparison and technical judgment, which is inefficient and has a high error rate, and cannot meet the needs of efficient automation.
By obtaining the metadata of the file to be verified, static rule checking and dynamic technical inspection, generating rule checking data and technical inspection data, and combining the verification model to perform hierarchical warning prompts to achieve automated verification.
It significantly improves document quality and compliance, reduces the risk of human error, improves the review efficiency and accuracy of nuclear power design documents, and shortens the review cycle.
Smart Images

Figure CN120373290A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of computer software, and particularly to a method, system, device and medium for verifying nuclear power design documents. Background Art
[0002] During the design process of a nuclear power plant, a large number of electronic documents are generated, including process documents, final product documents, etc. Multiple verification steps such as compilation, specification inspection, technical verification, and technical approval are required throughout the document life cycle, and each step may return the document to the compiler for modification due to problems found. In the prior art, when verifying a large number of electronic documents, manual comparison and technical judgment are mainly relied on. This method not only requires a large amount of manpower and time, but also has extremely low efficiency due to inevitable human errors. Therefore, there is an urgent need for a more efficient and reliable automated solution to improve the accuracy and efficiency of document review, reduce the dependence on human resources and the error rate. Summary of the Invention
[0003] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide a method, system, device and medium for verifying nuclear power design documents, which are used to solve the technical problems of low efficiency and high error rate existing in the prior art when verifying electronic documents by relying on manual comparison and technical judgment.
[0004] To achieve the above object and other related objects, the present invention provides a method for verifying nuclear power design documents, including:
[0005] Obtain a file to be verified, and extract metadata of the file to be verified;
[0006] Based on the metadata, perform static rule checking on the file to be verified to generate rule check data;
[0007] Perform dynamic technical checking on the file to be verified through a preset verification model to generate technical check data;
[0008] Based on the rule check data and the technical check data, generate file verification data, and perform hierarchical early warning prompts based on the file verification data.
[0009] In an embodiment of the present invention, the step of obtaining a file to be verified and extracting metadata of the file to be verified includes:
[0010] Obtain a file to be verified, and convert the file to be verified into a preset format;
[0011] Extract metadata from the file to be verified after format conversion, where the metadata includes file type and belonging stage.
[0012] In one embodiment of the present invention, the step of performing static rule checking on the file to be verified based on the metadata to generate rule check data includes:
[0013] Perform basic error detection on the file to be verified, and generate format check data according to the screened basic errors;
[0014] Based on the file type and the stage to which it belongs in the metadata, obtain the corresponding check template and check rules from the preset template library and rule library;
[0015] Based on the check template and the check rules, perform template compliance checking on the file to be verified to generate template check data;
[0016] Save the format check data and the template check data as rule check data.
[0017] In one embodiment of the present invention, the step of performing template compliance checking on the file to be verified based on the check template and the check rules to generate template check data includes:
[0018] Extract and compare the structure information of the file to be verified and the structure information of the check template to judge the structural integrity of the file to be verified;
[0019] Based on the check rules, judge the integrity of the required fields in the file to be verified;
[0020] Generate corresponding template check data based on the judgment result of the structural integrity and the judgment result of the integrity of the required fields.
[0021] In one embodiment of the present invention, the step of performing dynamic technical checking on the file to be verified through a preset verification model to generate technical check data includes:
[0022] Input the file to be verified into the preset verification model to extract technical parameters;
[0023] Compare the technical parameters with the historical data in the preset experience feedback database, and generate technical check data according to the comparison result.
[0024] In one embodiment of the present invention, the step of generating file verification data based on the rule check data and the technical check data, and performing hierarchical early warning prompts based on the file verification data includes:
[0025] Generate file verification data based on the rule check data and the technical check data;
[0026] Judge the error level corresponding to the file verification data;
[0027] When the error level is level one, generate and send a level-one warning message, which is characterized by a warning prompt through the side display bar of the display interface;
[0028] When the error level is level two, generate and send a level-two warning message, which is characterized by a warning prompt through a pop-up window of the display interface.
[0029] In an embodiment of the present invention, after the steps of generating file verification data based on the rule check data and the technical check data and performing hierarchical warning prompts based on the file verification data, the following steps are further included:
[0030] Obtain the file to be verified modified according to the level-one warning message or the level-two warning message;
[0031] Use the modified file to be verified as a new training set to perform incremental learning on the verification model to update the verification model.
[0032] The present invention also provides a verification system for nuclear power design documents, including:
[0033] A data extraction module, configured to obtain the file to be verified uploaded by a staff member and extract the metadata of the file to be verified;
[0034] A rule check module, configured to perform static rule checks on the file to be verified based on the metadata to generate rule check data;
[0035] A technical check module, configured to perform dynamic technical checks on the file to be verified through a preset verification model to generate technical check data;
[0036] A verification warning module, configured to generate file verification data based on the rule check data and the technical check data and perform hierarchical warning prompts based on the file verification data.
[0037] The present invention also provides an electronic device, and the electronic device includes:
[0038] One or more processors;
[0039] A storage device, configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the electronic device to implement the verification method for nuclear power design documents as described in any one of the above.
[0040] The present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is caused to execute the method for verifying a nuclear power design document described in any one of the above.
[0041] As described above, the method, system, device and medium for verifying a nuclear power design document of the present invention have the following beneficial effects: Through an automated inspection and intelligent early warning mechanism, the present invention significantly improves the document quality and compliance, accurately identifies format errors, technical parameter conflicts and specification deviations, and reduces the risk of human error. In the present invention, by combining a dynamic rule engine and a verification model with a historical experience database, the technical verification efficiency is improved, and by pushing the responsible person in a hierarchical early warning directionally, the review cycle is shortened. The present invention also ensures the accuracy and efficiency of engineering construction through risk pre-interception and full-process traceability. Description of the Drawings
[0042] Figure 1 It is a schematic flowchart of the method for verifying a nuclear power design document provided by an embodiment of the present invention;
[0043] Figure 2 It is shown as a structural block diagram of the system for verifying a nuclear power design document provided by an embodiment of the present invention;
[0044] Figure 3 It is shown as a schematic structural diagram of an electronic device according to an embodiment of the present invention. Detailed Embodiments
[0045] The following uses specific specific examples to illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.
[0046] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present invention in a schematic manner. Therefore, only the components related to the present invention are shown in the diagrams, rather than being drawn according to the number, shape and size of the components in actual implementation. The type, quantity and proportion of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.
[0047] In the following description, numerous specific details are explored to provide a more thorough explanation of the embodiments of the present invention. However, it is obvious to those skilled in the art that the embodiments of the present invention can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present invention difficult to understand.
[0048] The present invention provides a method, system, device, and medium for verifying nuclear power design documents, which relates to the field of computer software and can be applied to the approval process of nuclear power design documents. By applying this method in the document approval system, the full process automation from file upload to intelligent warning can be achieved, taking into account both efficiency and accuracy, and significantly improving the reliability of nuclear power design document management. The following is a detailed description through specific embodiments.
[0049] Please refer to Figure 1 , the present invention provides a method for verifying nuclear power design documents, which may include the following steps:
[0050] Step S100: Obtain the file to be verified and extract the metadata of the file to be verified;
[0051] Step S200: Based on the metadata, perform static rule checks on the file to be verified to generate rule check data;
[0052] Step S300: Perform dynamic technical checks on the file to be verified through a preset verification model to generate technical check data;
[0053] Step S400: Based on the rule check data and the technical check data, generate file verification data, and perform hierarchical warning prompts based on the file verification data.
[0054] In an embodiment of the present invention, when step S100 is executed, that is, the file to be verified is obtained and the metadata of the file to be verified is extracted. Specifically, during the design process of a nuclear power plant, a large number of electronic files are generated, such as site preliminary selection reports, preliminary feasibility study reports, site selection safety evaluation reports, environmental impact assessment reports, various special research reports, project proposals, feasibility study reports, and bill of quantities. Each electronic file needs to be uploaded to the document approval system and reviewed and verified by preset process personnel at all levels in turn. In this embodiment, the staff uploads the file to be verified through the Web interface or API interface provided by the document approval system. This step supports uploading files in multiple formats, such as.docx,.pdf,.xlsx, etc.
[0055] Further, after receiving the file to be verified, it is necessary to convert the file to be verified into a preset format. For example, convert a.pdf file into a text file. Then, perform metadata extraction processing on the file to be verified after format conversion. In this embodiment, the metadata may include, but is not limited to, file type, stage of belonging, and responsible person information. The metadata can be extracted by parsing the file content, extracting file attributes, and receiving user input, etc. For example, extract keywords or chapter titles through text parsing, or extract according to the document author, creation time, file extension, etc., or fill in manually when the file is uploaded or obtain from the system account association. Among them, the file type may include, for example, feasibility study reports, bill of quantities, etc. This information can be automatically extracted through the file extension of the file to be verified and content keywords (such as "general site selection" in the "feasibility study report"). The stage of belonging can be divided into, for example, site selection stage, preliminary design stage, final review stage, etc. This information can be obtained by parsing the chapter title (such as "preliminary design stage" corresponding to the "preliminary design" chapter) or user input. The responsible person may include file writers, checkers, document personnel, approvers, etc. This information can be obtained from file attributes (such as the Word author field) or system account association. Through the above methods, efficient and accurate metadata extraction can be achieved, providing structured input for subsequent rule checking and intelligent warning.
[0056] In an embodiment of the present invention, when step S200 is executed, that is, based on the metadata, perform static rule checking on the file to be verified to generate rule checking data. Specifically, it may include the following steps:
[0057] Step S210: Perform basic error detection on the file to be verified, and generate format check data according to the filtered basic errors;
[0058] Step S220: Based on the file type and stage of belonging in the metadata, obtain the corresponding check templates and check rules from the preset template library and rule library; based on the check templates and check rules, perform template compliance checking on the file to be verified to generate template check data; save the format check data and the template check data as rule check data.
[0059] In an embodiment of the present invention, when step S210 is executed, that is, basic error detection is performed on the file to be verified, and format check data is generated according to the filtered basic errors. Specifically, first, a custom dictionary in the nuclear power field is loaded, for example, terms such as "reactor" and "containment", and then the file to be verified is processed by sentence splitting the full text, and the spelling is checked word by word. During the check, proper nouns can be ignored, such as the plant name, and suspicious words are marked. For example, "anti-reactor" is recommended to be modified to "reactor". Then, punctuation check is performed on the file to be verified. For example, Chinese punctuation is standardized, full-width symbols are used instead of half-width symbols, and the mixing of Chinese and English punctuation is prohibited. Finally, based on a preset unit library, the unit format in the file to be verified is checked. The unit library predefines common units and their standard formats in the nuclear power design field, such as the pressure unit "MPa" and the temperature unit "℃". By extracting the numerical and unit combinations in the text and comparing them with the unit library, illegal units or capitalization errors are marked. Based on the above three types of basic format check information, corresponding format check data is generated.
[0060] In an embodiment of the present invention, when step S220 is executed, that is, based on the file type and the stage to which it belongs in the metadata, the corresponding check template and check rules are obtained from the preset template library and rule library; based on the check template and check rules, template compliance check is performed on the file to be verified, and template check data is generated; the format check data and the template check data are saved as rule check data. Specifically, it can be understood that the template library stores the check templates corresponding to various types of files, and the rule library stores the check rules corresponding to various types of files. Based on the information such as the file type and the stage to which it belongs in the metadata extracted in step S100, the check template and check rules corresponding to the file to be verified are obtained from the template library and the rule library respectively. In this embodiment, step S220 may specifically include the following steps:
[0061] Step S221: Extract and compare the structural information of the file to be verified and the structural information of the check template to judge the structural integrity of the file to be verified;
[0062] Step S222: Based on the check rules, judge the integrity of the required fields in the file to be verified;
[0063] Step S223: Based on the judgment results of the structural integrity and the judgment results of the integrity of the required fields, generate corresponding template check data.
[0064] In an embodiment of the present invention, when steps S221 to S223 are executed, specifically, first, the structural information of the file to be verified is extracted, and the structural information of the inspection template is extracted. For example, when the file to be verified is an Office document, python-docx can be used to parse the title and paragraph structure of the Word document. When the file to be verified is a PDF document: text and chapter titles are extracted through PyPDF2 or pdfplumber. Then, the structural information of the file to be verified extracted is compared with the structural information of the corresponding inspection template to determine the structural integrity of the file to be verified. Then, based on the obtained inspection rules, regular expression matching is performed on the text in each chapter of the file to be verified to check whether it contains required fields, that is, to determine the integrity of the required fields in the file to be verified. Based on the judgment results of the integrity of the above structure and the integrity of the required fields, corresponding template inspection data is generated.
[0065] Further, the format inspection data generated in step S210 and the template inspection data generated in step S220 are saved as rule inspection data.
[0066] In an embodiment of the present invention, when step S300 is executed, that is, a dynamic technical inspection is performed on the file to be verified through a preset verification model to generate technical inspection data;. Specifically, the following steps may be included:
[0067] Step S310: Input the file to be verified into the preset verification model to extract technical parameters;
[0068] Step S320: Compare the technical parameters with the historical data in the preset experience feedback database, and generate technical inspection data according to the comparison result.
[0069] In an embodiment of the present invention, when step S310 is executed, the file to be verified is input into a preset verification model to extract technical parameters. Specifically, first, the file to be verified is input into the preset verification model to extract technical parameters. For example, reactor power, safety threshold, etc. In this embodiment, the verification model is a dedicated NLP (Natural Language Processing) model in the field of nuclear power design that has been trained, such as the SciBERT model. This verification model has been fine-tuned for the verification requirements of nuclear power design documents. It supports the named entity recognition (NER) task and can identify technical parameters in the text (such as material properties, experimental conditions, numerical parameters, etc.). In this embodiment, the verification model can combine two natural language processing techniques, named entity recognition (NER) and relation extraction (RE), to extract specific technical parameters from the text of the file to be verified and understand the relationships between these parameters or between the parameters and other entities. The verification model can output a list of entities with tags.
[0070] Furthermore, the results can be filtered or corrected through regular expressions or a rule engine, and the extracted parameters can be sorted into structured data by category (such as JSON or CSV format).
[0071] In an embodiment of the present invention, when step S320 is executed, that is, the technical parameters are compared with the historical data in the preset experience feedback database, and technical inspection data is generated according to the comparison results. Specifically, the historical data of various types of technical parameters is stored in the experience feedback database, which may specifically include parameter names, standard values / ranges, applicable conditions, and historical cases, etc. In this embodiment, first, the technical parameters extracted in step S310 are subjected to parameter name matching, that is, the name differences are processed through fuzzy matching or a thesaurus. For example, "tensile strength" and "tensile strength". Then, the numerical values of the extracted technical parameters are compared with the standard values / ranges in the experience feedback database to check whether the parameter values meet the standard values / ranges (such as whether "500 MPa" is between "400 - 600 MPa"), or whether the discrete value requirements are met (such as "qualified / unqualified"). Next, whether the experimental conditions corresponding to the extended parameters (such as temperature, material type) are consistent with the applicable conditions in the database. If the parameter exceeds the threshold, deviates from the historical trend, or is abnormally associated with other parameters (such as "too high temperature" and "strength decrease" appear simultaneously), it is marked as "abnormal" or "requiring attention". The comparison results are sorted into structured data (such as JSON), including parameter names, extracted values, standard ranges, status (normal / abnormal), and remarks (such as reference standard clauses). Finally, the results are returned through an API for subsequent system calls, and the verification records are stored in the database to support traceability.
[0072] In an embodiment of the present invention, when step S400 is executed, that is, based on rule check data and technical check data, file verification data is generated, and a hierarchical warning prompt is made based on the file verification data. Specifically, the following steps may be included:
[0073] Step S410: Based on rule check data and technical check data, generate file verification data;
[0074] Step S420: Determine the error level corresponding to the file verification data; when the error level is level one, generate and send a level-one warning message, and the level-one warning message is characterized by a warning prompt through the side display bar of the display interface; when the error level is level two, generate and send a level-two warning message, and the level-two warning message is characterized by a warning prompt through a pop-up window of the display interface.
[0075] In an embodiment of the present invention, when step S410 is executed, that is, based on rule check data and technical check data, file verification data is generated. Specifically, the rule check data records static rule problems such as chapter missing, spelling mistakes, and unit format errors. The technical check data records dynamic verification problems such as technical parameter conflicts and non-compliance with specifications. In this embodiment, first, the rule check data and the technical check data are integrated into file verification data in a unified JSON format. Each error has a preset risk level mapping, and the risk level of each error is marked in the fields of the file verification data. For example, a fixable format or technical deviation (such as a unit error or a slight deviation in the parameter range) corresponds to a level-one error; problems directly affecting the integrity or security of the file (such as chapter missing and mandatory specification conflicts) correspond to a level-two error.
[0076] In an embodiment of the present invention, when step S420 is executed, that is, determine the error level corresponding to the file verification data; when the error level is level one, generate and send a level-one warning message, and the level-one warning message is characterized by a warning prompt through the side display bar of the display interface; when the error level is level two, generate and send a level-two warning message, and the level-two warning message is characterized by a warning prompt through a pop-up window of the display interface. Specifically, according to the risk level field in the file verification data, determine the error level corresponding to the error that appears in the file to be verified. For example, when only basic errors exist, determine that the error level is level one; when there are template compliance errors and / or technical errors, then determine that the error level is level two.
[0077] In this embodiment, when the error level is level one, a level-one warning message can be generated and sent to the corresponding responsible person. In this embodiment, the warning method for the level-one warning message is to display a warning bar on the right side of the file editing interface and list the level-one error list. The level-one warning allows the user to temporarily save the file, but the user needs to confirm "acknowledge the risk". The user can choose "confirm and ignore" or "correct immediately", and the system records the operation log.
[0078] When the error level is level two, a level-two warning message can be generated and sent to the corresponding responsible person. In this embodiment, the warning method for the level-two warning message is to forcefully pop up a warning window to display the error details and suggested measures. The level-two warning prohibits submitting the file until the user handles all level-two errors. After the user makes corrections, the file needs to be resubmitted, and the system automatically triggers a full-scale verification.
[0079] For example, the file "Site Safety Assessment Report" triggers a hierarchical warning. According to the file verification data, it is determined that there are level-one errors (such as the unit "Mpa" being incorrect) and level-two errors (such as the lack of the "Environmental Impact Assessment" chapter). At this time, the system will trigger the sidebar to display a prompt "Unit error on page 5: Mpa → MPa", and at the same time trigger a pop-up warning "Missing chapter: Environmental Impact Assessment". After receiving the warning message, the responsible person can lift the level-two warning after supplementing the missing chapter; after correcting the unit error and confirming, the level-one warning can be lifted. At this time, the file can be submitted to the next process for review.
[0080] In an embodiment of the present invention, the user modifies the file according to the warning prompt or marks a false alarm. The system can record the user feedback, optimize the verification model through supervised learning, update the experience feedback database, and incorporate new cases and rules. Specifically, it can include the following steps:
[0081] Step S510: Obtain the file modified according to the level-one warning message or the level-two warning message;
[0082] Step S520: Use the modified file as a new training set to perform incremental learning on the verification model to update the verification model.
[0083] In an embodiment of the present invention, when step S510 is executed, that is, to obtain the file modified according to the level-one warning message or the level-two warning message. Specifically, the user interface of the file approval system provides a re-upload entry, supporting the responsible person to upload the corrected file. The system can also automatically record the file version (such as V1.0 (original), V1.1 (corrected)) and associate it with the original warning information.
[0084] Furthermore, the modified file can be re-verified to check whether the file format is legal and prevent malicious file injection. Automatically trigger static rule checks (such as chapter integrity) and technical verification (such as parameter compliance) to ensure that the warning problems have been resolved in the modified file. After confirming that the warning problems in the modified file have been completely resolved, save it.
[0085] In an embodiment of the present invention, when step S520 is executed, the modified file is used as a new training set to perform incremental learning on the verification model to update the verification model. Specifically, first, positive samples and negative samples are extracted from the modified file. Among them, the positive samples are the modified compliant parameters, and the negative samples are the original error parameters. Only data annotation is performed on the file based on the positive samples and negative samples. Then, based on the existing pre-trained model (such as SciBERT), elastic weight consolidation (EWC) or incremental fine-tuning technology is used to learn new data while retaining old knowledge. Load the current version of the verification model from the model repository, mix the new data with the historical data, where the new data accounts for 70%, and 30% of the historical data is randomly selected to form a new training set. Train the verification model based on the new training set to update its model parameters. Then, verify the trained verification model to determine that it meets the target performance. Finally, deploy the updated verification model in the file approval system. As can be seen from the above, the verification model in the present invention can achieve continuous evolution, improving the accuracy and reliability of nuclear power design file verification.
[0086] Please refer to Figure 2 , the present invention also provides a verification system for nuclear power design files, which corresponds one-to-one with the verification method in the above embodiment. The verification system may include a data extraction module 11, a rule check module 12, a technical check module 13, and a verification warning module 14. The detailed description of each functional module is as follows:
[0087] The data extraction module 11 can be used to obtain the file to be verified and extract the metadata of the file to be verified. Further, the data extraction module 11 can be specifically used to obtain the file to be verified uploaded by the staff, convert the file to be verified into a preset format; extract the metadata from the file to be verified after format conversion, and the metadata includes the file type, the stage to which it belongs, and the responsible person.
[0088] A rule checking module 12 is configured to perform static rule checking on a file to be verified based on metadata, so as to generate rule checking data. Further, the rule checking module 12 may be specifically configured to perform basic error detection on the file to be verified, and generate format checking data according to the screened spelling errors, symbol errors, and / or unit format errors; obtain corresponding checking templates and checking rules from a preset template library and rule library based on the file type and the stage to which the file belongs in the metadata; perform template compliance checking on the file to be verified based on the checking templates and checking rules, and generate template checking data; and save the format checking data and the template checking data as rule checking data.
[0089] A technical checking module 13 is configured to perform dynamic technical checking on a file to be verified through a preset verification model, and generate technical checking data. Further, the technical checking module 13 may be specifically configured to input the file to be verified into the preset verification model to extract technical parameters; compare the technical parameters with historical data in a preset experience feedback database, and generate technical checking data according to the comparison result.
[0090] A verification warning module 14 is configured to generate file verification data based on the rule checking data and the technical checking data, and perform hierarchical warning prompts based on the file verification data. Further, the verification warning module 14 may be specifically configured to generate file verification data based on the rule checking data and the technical checking data; determine the error level corresponding to the file verification data: when the error level is level one, generate and send a level one warning message to the person in charge corresponding to the person in charge information, and the level one warning message is characterized by a warning prompt through the side display bar of the display interface; when the error level is level two, generate and send a level two warning message to the person in charge corresponding to the person in charge information, and the level two warning message is characterized by a warning prompt through a pop-up window of the display interface.
[0091] For the specific limitations of the verification system for nuclear power design documents, reference may be made to the limitations on the verification method in the foregoing text, which will not be elaborated here. Each module in the foregoing verification system may be implemented in whole or in part by software, hardware, and their combination. The foregoing modules may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the foregoing modules.
[0092] An embodiment of the present invention further provides an electronic device, including: one or more processors; a storage device configured to store one or more programs, and when the one or more programs are executed by the one or more processors, enable the electronic device to implement the verification method for nuclear power design documents provided in the foregoing various embodiments.
[0093] Please refer to Figure 3, the electronic device 2 may include a memory 21, a processor 22, and a bus. It may also include a computer program stored in the memory 21 and executable on the processor 22, such as a verification program for nuclear power design documents.
[0094] Among them, the memory 21 includes at least one type of readable storage medium, which includes flash memory, mobile hard disks, multimedia cards, card-type memories (such as SD or DX memories, etc.), magnetic memories, magnetic disks, optical disks, etc. In some embodiments, the memory 21 may be an internal storage unit of the electronic device 2, such as the mobile hard disk of the electronic device 2. In some other embodiments, the memory 21 may also be an external storage device of the electronic device 2, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 2. Further, the memory 21 may also include both an internal storage unit and an external storage device of the electronic device 2. The memory 21 can be used not only to store application software installed on the electronic device 2 and various types of data, such as the code for verifying nuclear power design documents, but also to temporarily store data that has been output or will be output.
[0095] In some embodiments, the processor 22 may be composed of integrated circuits. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same or different functions, including a combination of one or more Central Processing Units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips, etc. The processor 22 is the control core of the electronic device 2, connecting various components of the entire electronic device 2 through various interfaces and lines. By running or executing programs or modules stored in the memory 21 (such as a training program for a fatigue prediction model, etc.), and by calling data stored in the memory 21, it executes various functions of the electronic device 2 and processes data.
[0096] The processor 22 executes the operating system of the electronic device 2 and various installed application programs. The processor 22 executes the application programs to implement the steps in the above-mentioned method for verifying nuclear power design documents.
[0097] Exemplarily, the computer program may be divided into one or more modules, which are stored in the memory 21 and executed by the processor 22 to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the electronic device 2. For example, the computer program may be divided into a data extraction module 11, a rule checking module 12, a technical checking module 13, and a verification warning module 14.
[0098] The above-mentioned integrated unit implemented in the form of a software function module can be stored in a computer-readable storage medium, and the computer-readable storage medium can be non-volatile or volatile. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to perform part of the functions of the verification method of the nuclear power design file described in each embodiment of the present application.
[0099] In summary, the present invention discloses a verification method, system, equipment and medium for nuclear power design documents, which relate to the field of software technology. Through automated inspection and intelligent early warning mechanisms, the quality and compliance of documents are significantly improved, format errors, technical parameter conflicts and specification deviations are accurately identified, and the risk of human errors is reduced. In the present invention, the efficiency of technical verification is improved by combining a dynamic rule engine and a verification model with a historical experience database, and the review cycle is shortened by targeted push notifications to responsible persons through graded early warnings. The present invention also ensures the accuracy and efficiency of engineering construction through risk pre-interception and full-process tracing. Therefore, the present invention effectively overcomes the various shortcomings of the prior art and has a high industrial utilization value.
[0100] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.
Claims
1. A verification method for nuclear power design documents, characterized in that, Including: Obtain the file to be verified and extract the metadata of the file to be verified; Based on the metadata, perform static rule checks on the file to be verified to generate rule check data; Perform dynamic technical checks on the file to be verified through a preset verification model to generate technical check data; Based on the rule check data and the technical check data, generate file verification data and perform hierarchical early warning prompts based on the file verification data.
2. The verification method of nuclear power design documents according to claim 1, characterized in that The step of obtaining the file to be verified and extracting the metadata of the file to be verified includes: Obtain the file to be verified and convert the file to be verified into a preset format; Extract metadata from the file to be verified after format conversion, and the metadata includes file type and belonging stage.
3. The verification method of nuclear power design documents according to claim 2, characterized in that The step of performing static rule checks on the file to be verified based on the metadata to generate rule check data includes: Perform basic error detection on the file to be verified and generate format check data according to the selected basic errors; Based on the file type and belonging stage in the metadata, obtain the corresponding check templates and check rules from the preset template library and rule library; Based on the check templates and the check rules, perform template compliance checks on the file to be verified to generate template check data; Save the format check data and the template check data as rule check data.
4. The verification method of nuclear power design documents according to claim 3, characterized in that The step of performing template compliance checks on the file to be verified based on the check templates and the check rules to generate template check data includes: Extract and compare the structure information of the file to be verified and the structure information of the check template to judge the structural integrity of the file to be verified; Based on the check rules, judge the integrity of the required fields in the file to be verified; Generate corresponding template check data based on the judgment results of the structural integrity and the judgment results of the integrity of the required fields.
5. The verification method of the nuclear power design document according to claim 1, characterized in that, The step of performing dynamic technical checks on the file to be verified through a preset verification model to generate technical check data includes: Input the file to be verified into a preset verification model and extract technical parameters; Compare the technical parameters with the historical data in the preset experience feedback database and generate technical check data according to the comparison results.
6. The verification method for nuclear power design documents according to claim 2, characterized in that, The step of generating file verification data based on the rule check data and the technical check data and performing hierarchical early warning prompts based on the file verification data includes: Generate file verification data based on the rule check data and the technical check data; Judge the error level corresponding to the file verification data; When the error level is level one, generate and send a level one early warning message, and the level one early warning message is characterized by an early warning prompt through the side display bar of the display interface; When the error level is level two, generate and send a level two early warning message, and the level two early warning message is characterized by an early warning prompt through a pop-up window of the display interface.
7. The verification method of the nuclear power design document according to claim 6, wherein After the step of generating file verification data based on the rule check data and technical check data and performing hierarchical early warning prompts based on the file verification data, it further includes: Obtain the file to be verified modified according to the first-level warning information or the second-level warning information; Use the modified file to be verified as a new training set to perform incremental learning processing on the verification model to update the verification model.
8. A verification system for nuclear power design documents, characterized in that, It includes: A data extraction module, which is used for the file to be verified and extracts the metadata of the file to be verified; A rule check module, which is used to perform static rule checks on the file to be verified based on the metadata to generate rule check data; A technical check module, which is used to perform dynamic technical checks on the file to be verified through a preset verification model to generate technical check data; A verification warning module, which is used to generate file verification data based on the rule check data and the technical check data, and perform hierarchical warning prompts based on the file verification data.
9. An electronic device, characterized in that: The electronic device includes: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the verification method of the nuclear power design file according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that, A computer program is stored thereon, which when executed by the processor of the computer, causes the computer to execute the verification method of the nuclear power design file according to any one of claims 1 to 7.
Citation Information
Cited By
Authorization plan processing method and device based on airworthiness authentication platform
CN121599440A