Method and device for generating specification citation information for nuclear power plant design text and related equipment

Abstract

The application provides a specification citation information generation method and device for nuclear power plant design texts and related equipment, relates to the field of nuclear power plant design file management, and comprises the following steps: acquiring a plurality of nuclear power plant design texts; determining, for each nuclear power plant design text, a specification query text corresponding to the nuclear power plant design text; performing clause query in a pre-constructed specification clause library based on the specification query text to obtain reference clause information matched with the specification query text; wherein the specification clause library performs a clause update operation once every preset period; and generating citation information matched with the nuclear power plant design text according to the reference clause information corresponding to the specification query text. The application can realize efficient reference association of the nuclear power plant design file and the standard clause and reduce human error.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of nuclear power plant design document management, and particularly to a method, apparatus, and related equipment for generating specification citation information for nuclear power plant design texts. Background Technology

[0002] In the design process of nuclear power plants, design documents are the core basis for the construction and operation of nuclear power plants, and must strictly adhere to regulatory standards and clauses to ensure safety and compliance. With the increasing standardization requirements of the nuclear power industry, design documents have gradually achieved digital storage through electronic document management and database technology, but the reference and matching of standard clauses still rely on manual operation.

[0003] In related technologies, the association between design documents and standard clauses is mainly achieved through manual annotation or static database retrieval. However, due to the lack of structured association between standard clauses and design documents, designers are prone to omissions or misuses when manually searching for and matching clauses. Summary of the Invention

[0004] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application provides a method and related equipment for generating specification citation information in nuclear power plant design documents, which can achieve efficient citation association between nuclear power plant design documents and standard clauses, reducing human error.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for generating specification citation information for nuclear power plant design texts, including:

[0006] Obtain design documents for multiple nuclear power plants;

[0007] For each of the aforementioned nuclear power plant design documents, determine the corresponding specification query text for that nuclear power plant design document;

[0008] Based on the standard query text, a clause query is performed in a pre-built standard clause library to obtain the reference clause information that matches the standard query text; wherein, the standard clause library performs a clause update operation once every preset period;

[0009] Based on the reference clause information corresponding to the specified query text, citation information matching the nuclear power plant design text is generated.

[0010] In some embodiments, the pre-construction process of the specification clause library includes:

[0011] Obtain multiple specification clause texts;

[0012] Text recognition is performed on each of the aforementioned normative clauses to extract multiple normative clauses and text attribute information for each of the aforementioned normative clauses; the text attribute information includes text number and text version number;

[0013] For each of the aforementioned normative clauses, the paradigm clause information is constructed based on the text attribute information corresponding to the normative clause and the text to which the normative clause belongs;

[0014] The normative clause library is constructed based on information from multiple paradigm clauses.

[0015] In some embodiments, the step of performing a clause search in a pre-built specification clause library based on the specification query text to obtain reference clause information matching the specification query text includes:

[0016] Based on the specified query text, a fuzzy search and matching is performed on multiple paradigm clause information to determine multiple candidate paradigm clause information;

[0017] Calculate the relevance score between each candidate paradigm clause and the normative query text;

[0018] Based on the relevance score, the information of multiple candidate paradigm clauses is sorted to obtain and display a list of candidate paradigm clause information.

[0019] In response to a selection operation for the candidate paradigm clause information list, the reference clause information matching the specification query text is determined based on the selection operation.

[0020] In some embodiments, calculating the relevance score between each candidate paradigm clause and the canonical query text includes:

[0021] Obtain the number of keyword matches between each candidate paradigm clause and the standard query text;

[0022] The relevance score of the candidate paradigm clause information is calculated based on the number of keyword matches.

[0023] In some embodiments, sorting the candidate paradigm clause information based on the relevance score to obtain and display a list of candidate standard clauses includes:

[0024] The candidate paradigm clause information is sorted based on the relevance score;

[0025] The candidate paradigm clauses are displayed in descending order of relevance score, and the matching fields that successfully match the normative query text are highlighted.

[0026] In some embodiments, after generating citation information matching the nuclear power plant design text based on the citation clause information corresponding to the specification query text, the method further includes:

[0027] Based on each nuclear power plant design text and the corresponding cited information, generate nuclear power plant design documents;

[0028] All cited information in the nuclear power plant design documents is parsed to obtain the text attribute information and the specification clauses corresponding to each cited information;

[0029] Based on the text attribute information corresponding to each of the aforementioned standard clauses, a multi-level mapping relationship between the nuclear power plant design documents and the standard clause library is constructed; wherein, the multi-level mapping relationship includes a first mapping relationship between the nuclear power plant design documents and the standard clause library, and a second mapping relationship between the standard clause library and the standard clauses;

[0030] The multi-level mapping relationship is stored in the form of a structured table as the reference association table.

[0031] In some embodiments, after storing the multi-level mapping relationship as the reference association table in the form of a structured table, the method further includes:

[0032] Based on the reference association table, traverse the normal form clause information corresponding to all referenced clause information in the nuclear power plant design document;

[0033] For each of the aforementioned paradigm clauses, the corresponding normative clause library is determined according to the second mapping relationship;

[0034] Obtain the original clause information from the standard clause library, and compare the paradigm clause information with the original clause information;

[0035] When a difference is detected between the paradigm clause information and the original clause information, a difference location marker is generated and a content verification alarm is triggered.

[0036] In some embodiments, after storing the multi-level mapping relationship as the reference association table in the form of a structured table, the method further includes:

[0037] In response to detecting an update to the version number of the text of the specification clause, the revised clause information is retrieved from the text of the specification clause;

[0038] The nuclear power plant design documents are obtained by querying multiple design documents based on the text number of the specified clause and the first mapping relationship.

[0039] Based on the revised clause information and the second mapping relationship, the paradigm clause information corresponding to the revised clause information is obtained by querying the nuclear power plant design documents.

[0040] The paradigm clause information is updated based on the revised clause information.

[0041] In some embodiments, after constructing the paradigm clause information for each of the standard clauses based on the clause attribute information corresponding to the standard clause and the normative clause library to which the standard clause belongs, the method further includes:

[0042] Each of the aforementioned paradigm clauses is categorized and labeled according to a preset classification rule, generating a corresponding clause category label; wherein, the clause category label includes design compliance clauses, design reference clauses, and downstream execution clauses.

[0043] In some embodiments, classifying and labeling each paradigm clause information according to a preset classification rule includes:

[0044] The paradigm clause information is subjected to mandatory compliance keyword matching. When the paradigm clause information is successfully matched with the mandatory compliance keyword, the clause is marked as a design compliance clause.

[0045] The paradigm clause information is matched with suggested keywords. When the paradigm clause information is successfully matched with the suggested keywords and no mandatory compliance keyword matching is triggered, the clause is marked as a design reference clause.

[0046] The paradigm clause information is matched with execution instruction keywords. When a successful match is found between the paradigm clause information and the execution instruction keywords, the clause is marked as a downstream execution clause.

[0047] The reference association table of the target design document is classified and statistically analyzed based on the aforementioned clause category labels, generating a reference distribution report that includes the design compliance clauses, design reference clauses, and downstream execution clauses.

[0048] Secondly, embodiments of this application provide a device for generating specification citation information for nuclear power plant design texts, comprising:

[0049] The acquisition module is used to acquire design documents for multiple nuclear power plants;

[0050] The determination module is used to determine the specification query text corresponding to each nuclear power plant design text.

[0051] The query module is used to perform clause queries in a pre-built standard clause library based on the standard query text to obtain reference clause information that matches the standard query text; wherein, the standard clause library performs a clause update operation once every preset period;

[0052] The generation module is used to generate citation information that matches the nuclear power plant design text based on the reference clause information corresponding to the reference text in the specification query text.

[0053] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for generating specification citation information for nuclear power plant design text as described in any one of the embodiments of the first aspect of this application.

[0054] Fourthly, embodiments of this application provide a computer-readable storage medium storing a program that is executed by a processor to implement the method for generating specification citation information for nuclear power plant design texts as described in any one of the embodiments of the first aspect of this application.

[0055] The method for generating specification citation information for nuclear power plant design texts proposed in this application includes: acquiring multiple nuclear power plant design texts; determining a specification query text corresponding to each nuclear power plant design text; performing a clause query in a pre-built specification clause library based on the specification query text to obtain the reference clause information matching the specification query text; wherein the specification clause library performs a clause update operation once every preset period; and generating citation information matching the nuclear power plant design text based on the reference clause information corresponding to the specification query text.

[0056] This application acquires multiple nuclear power plant design documents, identifies a corresponding specification query text for each document, extracts key information from each design document, and further searches a pre-built specification clause library based on the specification query text to obtain matching reference clause information, thus achieving automatic association between design documents and specification clauses. Specifically, the specification clause library is updated every preset period to ensure its timeliness and accuracy, avoiding citation errors due to outdated specification clauses. Finally, based on the reference clause information corresponding to the specification query text, citation information matching the nuclear power plant design documents is generated, providing designers with clear and accurate specification references. Compared to existing technologies that rely on manual annotation or static database retrieval, the method provided in this application achieves dynamic association between design documents and specification clauses through automated text processing and clause matching, avoiding omissions or misuse problems in the manual search and matching process. In summary, this application can achieve efficient citation association between nuclear power plant design documents and standard clauses, reducing human error.

[0057] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description, claims and drawings. Attached Figure Description

[0058] Figure 1 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts according to an embodiment of this application.

[0059] Figure 2 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0060] Figure 3 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0061] Figure 4 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0062] Figure 5 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0063] Figure 6 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0064] Figure 7 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0065] Figure 8 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0066] Figure 9 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0067] Figure 10 This is a flowchart illustrating a method for generating specification citation information for nuclear power plant design texts, provided in another embodiment of this application.

[0068] Figure 11 This is a schematic diagram illustrating the framework of the application and management system of regulatory and standard provisions provided in one embodiment of this application in nuclear power plant design;

[0069] Figure 12 This is a schematic diagram of a specification citation information generation device for nuclear power plant design texts provided in an embodiment of this application;

[0070] Figure 13 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0071] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0072] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0073] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0074] As highly complex industrial facilities with extremely high safety requirements, nuclear power plants must strictly adhere to national regulations and industry standards throughout their entire lifecycle, from design and construction to operation and maintenance. Design documents, as the core carrier of nuclear power plant engineering activities, contain critical information such as system design parameters, process flows, and safety assessments; their compliance directly affects the safety and reliability of the nuclear power plant. However, with the expansion of nuclear power projects and the accelerated pace of technological iteration, the traditional management model relying on manual correlation of standard clauses is no longer sufficient to meet the needs for efficient and accurate compliance verification.

[0075] In existing technologies, the association between design documents and standard clauses is mainly achieved through two methods: first, designers manually annotate relevant clauses based on experience and cite them item by item in the document; second, standard clause numbers or keywords are retrieved from static databases for simple text matching. However, these methods have significant drawbacks: first, the efficiency and consistency of manual annotation are limited by the professional level and experience of designers, and subjective differences in understanding can easily lead to omissions or misuse of clause citations; second, static databases have long clause update cycles and lagging version management, making it difficult to track the dynamic revisions of regulations and standards in real time, resulting in a disconnect between cited content and current requirements.

[0076] Based on this, embodiments of this application provide a method, apparatus, and related equipment for generating specification citation information for nuclear power plant design documents, which can achieve efficient citation association between nuclear power plant design documents and standard clauses, and reduce human error.

[0077] The method, apparatus, and related equipment for generating specification citation information for nuclear power plant design texts provided in this application are specifically described through the following embodiments. First, the method for generating specification citation information for nuclear power plant design texts in this application embodiment is described.

[0078] The method for generating specification citation information for nuclear power plant design texts provided in this application relates to the field of nuclear power plant design document management. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the method for generating specification citation information for nuclear power plant design texts, but is not limited to the above forms.

[0079] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0080] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0081] Figure 1 This is an optional flowchart of a method for generating specification citation information for nuclear power plant design texts provided in this application embodiment. Figure 1 The methods may include, but are not limited to, steps 101 to 104.

[0082] Step 101: Obtain multiple nuclear power plant design documents.

[0083] Step 102: For each nuclear power plant design document, determine the corresponding specification query document.

[0084] Step 103: Based on the standard query text, perform a clause search in the pre-built standard clause library to obtain the referenced clause information that matches the standard query text.

[0085] Step 104: Generate citation information matching the nuclear power plant design text by querying the reference clause information corresponding to the text in the specification.

[0086] Steps 101 to 104 of this embodiment involve acquiring multiple nuclear power plant design documents, determining the corresponding specification query text for each document, extracting key information from each design document, and further querying a pre-built specification clause library based on the specification query text to obtain matching reference clause information. This achieves automatic association between the design documents and specification clauses. Specifically, the specification clause library is updated every preset period to ensure its timeliness and accuracy, avoiding citation errors due to outdated clauses. Finally, based on the reference clause information corresponding to the specification query text, citation information matching the nuclear power plant design documents is generated, providing designers with clear and accurate specification references. Compared to existing technologies that rely on manual annotation or static database retrieval, the method provided in this embodiment achieves dynamic association between design documents and specification clauses through automated text processing and clause matching, avoiding omissions or misuses during manual searching and matching. In summary, this application enables efficient association between nuclear power plant design documents and standard clauses, reducing human error.

[0087] In step 101 of some embodiments, it is first necessary to obtain multiple nuclear power plant design documents. Here, "nuclear power plant design documents" refers to text fragments generated during the nuclear power plant design process that require reference to relevant regulatory clauses. These text fragments are typically contained in various types of nuclear power plant design documents, such as system design specifications, equipment technical specifications, calculation sheets, and drawing descriptions. Each nuclear power plant design document may contain multiple text fragments requiring reference to regulations, i.e., multiple "nuclear power plant design documents." These nuclear power plant design documents can be selected and determined by the document drafters as needed to ensure that all places requiring reference to regulations are accurately marked.

[0088] In step 102 of some embodiments, for each acquired nuclear power plant design document, it is necessary to determine its corresponding specification query text. The "specification query text" can be key information extracted from the nuclear power plant design document for querying in the specification clause library, or it can be manually entered by the document drafter. The extraction process can be implemented using natural language processing (NLP) technology, keyword extraction algorithms, or manual annotation. The specification query text typically contains key technical terms, design parameters, equipment names, etc., from the nuclear power plant design document, accurately reflecting the technical content and specification requirements involved in the design document. The purpose of determining the specification query text is to transform the design document into a form that can be effectively queried in the specification clause library.

[0089] In step 103 of some embodiments, based on the determined specification query text, a clause search is performed in a pre-built specification clause library to obtain referenced clause information that matches the specification query text. The "specification clause library" is a structured database containing all relevant nuclear power regulations, standards, and specifications. This database not only stores the original text of the specification clauses but also includes metadata information such as clause numbers, titles, scope of application, and keywords to facilitate fast and accurate queries. To ensure the timeliness and accuracy of the specification clause library, the database needs to perform clause updates every preset period, such as weekly, monthly, or quarterly, to ensure that the latest specification changes are included. The query process can employ full-text search, semantic search, or knowledge graph-based reasoning techniques to achieve precise matching between the specification query text and the specification clauses. "Referenced clause information" refers to the specific content of the specification clauses that match the specification query text, including clause numbers, original text, etc.

[0090] Please see Figure 2 In some embodiments, the pre-construction process of the specification clause library may include, but is not limited to, steps 201 to 204.

[0091] Step 201: Obtain multiple standard clause texts.

[0092] Step 202: Perform text recognition on each standard clause text to extract multiple standard clauses and the text attribute information of each standard clause text.

[0093] Step 203: For each normative clause, construct the paradigm clause information based on the text attribute information corresponding to the normative clause and the normative clause text to which the normative clause belongs.

[0094] Step 204: Construct a standard clause library based on information from multiple paradigm clauses.

[0095] In step 201 of some embodiments, it is first necessary to obtain multiple regulatory clause texts. Here, "regulatory clause texts" refers to original documents containing relevant laws, standards, and specifications in the nuclear power field. These documents can be electronic (such as PDF or Word documents) or scanned paper copies. The sources of these regulatory clause texts include, but are not limited to, national regulations, industry association standards, International Atomic Energy Agency (IAEA) safety standards, and internal technical specifications of enterprises.

[0096] In step 202 of some embodiments, text recognition is performed on each acquired specification clause text to extract multiple specification clauses and text attribute information for each specification clause text. "Text recognition" refers to using Optical Character Recognition (OCR) technology (for scanned documents) or text parsing technology (for electronic documents) to convert the content in the specification clause text into an editable and searchable text format. Then, natural language processing (NLP) technology, rule engines, or machine learning models are used to identify and extract each individual specification clause from the text. A "specification clause" refers to the smallest independent unit in a specification document with clearly defined requirements, usually identified by a clause number. Simultaneously, "text attribute information" also needs to be extracted, which includes, but is not limited to, text number (e.g., standard number, regulation number) and text version number (used to identify the version of the specification, such as 2023 version, 2024 version, etc.). This information is crucial for subsequently constructing specification clause information.

[0097] In step 203 of some embodiments, for each extracted normative clause, it is associated with the text attribute information of its corresponding normative clause text to construct paradigm clause information. "Paradoxical clause information" refers to a data record that structurally integrates a normative clause with its source information (i.e., text attribute information). This association ensures that each normative clause can be traced back to its original source, including the specific normative document, version, and clause number. For example, a paradigm clause information might contain the following: {Clause Number: XXX, Clause Content: [Original Clause Text], Text Number: YYY, Text Version Number: ZZZ}. This structured data representation facilitates subsequent normative clause querying and management.

[0098] In step 204 of some embodiments, all the constructed paradigm clause information is integrated to build a normative clause library. This "normative clause library" is a structured database used to store and manage all paradigm clause information. The database can be built using a relational database (such as MySQL or Oracle) or a NoSQL database (such as MongoDB). The normative clause library not only stores paradigm clause information but also provides a query interface, supporting fast retrieval based on keywords, clause numbers, text numbers, version numbers, and other methods.

[0099] Through steps 201 to 204, this embodiment of the application constructs a traceable, searchable, and easily manageable normative clause library by structuring the original normative clause text. Specifically, through text recognition and information extraction, unstructured normative text is transformed into structured normative clause information; by associating normative clauses with their textual attribute information, the traceability and accuracy of the normative clauses are ensured; and by constructing the normative clause library, centralized management and efficient retrieval of normative clauses are achieved. This normative clause library provides a reliable data foundation for subsequent normative citations, avoiding the tedious process of manually reviewing a large number of normative documents, and improving the efficiency and accuracy of normative citations.

[0100] Please see Figure 3 In some embodiments, the steps may include, but are not limited to, steps 301 to 304.

[0101] Step 301: Perform fuzzy search matching on multiple paradigm clause information according to the standard query text to determine multiple candidate paradigm clause information.

[0102] Step 302: Calculate the relevance score between the information of each candidate paradigm clause and the normative query text.

[0103] Step 303: Sort the information of multiple candidate paradigm clauses based on relevance scores, and obtain and display the list of candidate paradigm clause information.

[0104] Step 304: In response to the selection operation for the candidate paradigm clause information list, determine the referenced clause information that matches the specification query text based on the selection operation.

[0105] In step 301 of some embodiments, "fuzzy search matching" refers to searching for paradigmatic clauses in the specification clause library that are similar to or related to the specification query text, even if they are not completely identical. This search method can tolerate a certain degree of spelling errors, synonym substitutions, or differences in expression. Fuzzy search can be implemented using various algorithms, such as algorithms based on edit distance, algorithms based on N-grams, or algorithms based on vector space models. Through fuzzy search, the search scope can be expanded, the recall rate can be improved, and relevant specification clauses can be avoided due to subtle differences in the specification query text. Multiple paradigmatic clause information is a set of paradigmatic clause information that may be related to the specification query text after preliminary screening by fuzzy search. For example, when the specification query text contains "containment leakage rate limit", all clauses in the clause library that involve keywords such as "leakage rate", "containment", and "limit" can be matched, ignoring differences in expression (such as synonym substitutions of "leakage rate" and "leakage rate"), to form an initial candidate set, avoiding the missed detection problem caused by traditional exact matching.

[0106] In step 302 of some embodiments, a relevance score is calculated for each candidate paradigm clause information and the canonical query text. The "relevance score" is a numerical value used to quantify the degree of relevance between the candidate paradigm clause information and the canonical query text. A higher score indicates a stronger relevance. The relevance score can be calculated based on various factors, such as text similarity, keyword matching, and semantic relevance. Commonly used calculation methods include the TF-IDF algorithm, the BM25 algorithm, or semantic similarity models based on deep learning. By calculating the relevance score, the candidate paradigm clause information can be ranked, with the most relevant clauses placed first.

[0107] Please see Figure 4 In some embodiments, step 302 may include, but is not limited to, steps 401 to 402.

[0108] Step 401: Obtain the number of keyword matches between the information of each candidate paradigm clause and the standard query text.

[0109] Step 402: Calculate the relevance score of candidate paradigm clause information based on the number of keyword matches.

[0110] In step 401 of some embodiments, "keyword match count" refers to the number of times a keyword appears in the canonical query text within the candidate paradigm clause information. Here, "keyword" can be extracted from the canonical query text or can be predefined technical terms related to the nuclear power field. The keyword match count can be calculated using a simple string matching algorithm.

[0111] In step 402 of some embodiments, the number of keyword matches is directly used as the relevance score; that is, the more matches, the higher the score. More complex calculation methods can consider factors such as keyword weight, keyword position in the normative clause information, and the length of the normative clause information, weighting and normalizing the number of keyword matches to obtain a more accurate relevance score. For example, the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm can be used, which comprehensively considers the frequency (TF) of the keyword in the current normative clause information and its rarity (IDF) in the entire normative clause library, thereby more accurately assessing the importance of the keyword.

[0112] Through steps 401 and 402, this embodiment achieves a preliminary assessment of the relevance of candidate paradigm clause information using the simple yet effective indicator of keyword matching frequency. Specifically, the keyword matching frequency reflects the textual similarity between the candidate paradigm clause information and the normative query text; a higher matching frequency generally indicates higher relevance. This keyword matching-based relevance calculation method is simple to implement, computationally efficient, and suitable for rapid retrieval of large-scale normative clause databases.

[0113] In step 303 of some embodiments, multiple candidate paradigm clause information are sorted based on relevance scores to obtain and display a candidate paradigm clause information list. The "candidate paradigm clause information list" is a sequence of paradigm clause information arranged from highest to lowest relevance score. This list is presented to users (e.g., designers) in a visual manner for easy browsing and selection. The displayed content typically includes a summary of the paradigm clause information, such as text number, clause number, and partial clause content, to help users quickly determine its relevance.

[0114] Please see Figure 5 In some embodiments, step 303 may include, but is not limited to, steps 501 to 502.

[0115] Step 501: Sort the information of multiple candidate paradigm clauses based on relevance scores.

[0116] Step 502: Display multiple candidate paradigm clause information in descending order of relevance score, and highlight the matching fields in the candidate paradigm clause information that successfully match the normative query text.

[0117] In step 501 of some embodiments, the sorting algorithm can be a common sorting algorithm, such as quicksort or mergesort, to arrange the candidate paradigm clause information in descending order of relevance score. The purpose of sorting is to place the most relevant candidate paradigm clause information first, making it convenient for users to view it first.

[0118] In step 502 of some embodiments, the sorted candidate paradigm clause information is presented to the user in a list or other visual format. Typically, not only the full content of the paradigm clause information is displayed, but also its summary information, such as clause number, title, and some key content, to facilitate quick browsing. "Highlighting" refers to specially marking the "matching fields" (i.e., keywords or phrases) in the candidate paradigm clause information that successfully match the normative query text, such as changing font color, bolding, or adding background color, to make them more visually prominent. This highlighting method helps users quickly locate the matching content, improving browsing efficiency.

[0119] Through steps 501 and 502, this embodiment improves the readability and understandability of candidate paradigm clause information by sorting and highlighting. Specifically, sorting places the most relevant clauses first, reducing the time users spend searching for the information they need; highlighting emphasizes matching content, helping users quickly locate key information. This optimized display design improves the user experience, enabling users to find the required normative clauses more quickly and accurately, thereby improving the efficiency and accuracy of normative citation.

[0120] In step 304 of some embodiments, in response to a selection operation on the candidate paradigm clause information list, the referenced clause information matching the normative query text is determined based on the selection operation. The "selection operation" refers to the user's action of selecting one or more paradigm clauses that best meet their needs after browsing the candidate paradigm clause information list. This operation can be achieved through clicking, checking boxes, etc. Based on the user's selection operation, the "referenced clause information" that ultimately matches the normative query text is determined, i.e., the normative clauses that the user confirms are referenced.

[0121] Through steps 301 to 304, this embodiment achieves precise matching of normative clauses by combining fuzzy search, relevance ranking, and user confirmation. Specifically, fuzzy search expands the search scope and improves recall; relevance ranking places the most relevant clauses first, improving retrieval efficiency; and the user confirmation mechanism ensures the accuracy of the final cited normative clauses. This matching method, which combines automated retrieval and manual confirmation, not only improves the efficiency of normative citation but also avoids errors that may arise from full automation, ensuring the accuracy and reliability of normative citation.

[0122] In step 104 of some embodiments, citation information matching the nuclear power plant design text is generated based on the referenced clause information corresponding to the query text in the specification. "Citation information" refers to specific information inserted into the nuclear power plant design text to indicate the referenced specification clause. Citation information may include the specification clause number, version number, etc., and may also include a link to the corresponding clause in the specification clause library. The citation information can be generated using a template-based approach, inserting the referenced clause information into the appropriate position in the nuclear power plant design text according to a predefined format. The generation of citation information allows readers of the design documents to clearly understand the specification clauses upon which the design text is based, facilitating subsequent review and verification.

[0123] Please see Figure 6 In some embodiments, steps 601 to 604 may be included after step 104.

[0124] Step 601: Generate nuclear power plant design documents based on each nuclear power plant design text and its corresponding citation information.

[0125] Step 602: Parse all the reference information in the nuclear power plant design documents to obtain the text attribute information and specification clauses corresponding to each reference information.

[0126] Step 603: Based on the text attribute information corresponding to each specification clause, construct a multi-level mapping relationship between nuclear power plant design documents and the specification clause library.

[0127] Step 604: Store the multi-level mapping relationship as a reference association table in the form of a structured table.

[0128] In step 601 of some embodiments, the previously generated citation information is integrated into the corresponding nuclear power plant design text to form a complete nuclear power plant design document with regulatory references. The integration process can employ text editing techniques to insert the citation information into appropriate locations within the nuclear power plant design text, such as at the end of relevant paragraphs or as footnotes or endnotes. The generated nuclear power plant design document is the final deliverable, containing design content and regulatory reference information.

[0129] In step 602 of some embodiments, "parsing" refers to extracting structured data from the cited information. Since the cited information contains source information of the normative clauses (such as text number, version number, clause number, etc.), parsing can obtain this "text attribute information" and the corresponding original text of the "normative clauses".

[0130] In step 603 of some embodiments, "multi-level mapping relationship" refers to establishing the association between nuclear power plant design documents, the standard clause library, and specific standard clauses. Specifically, the "first mapping relationship" refers to the association between nuclear power plant design documents and the standard clause library, i.e., which design document references which standard clause library (or which standards within it); the "second mapping relationship" refers to the association between the standard clause library and standard clauses, i.e., which specific standard clauses in the standard clause library are referenced by the nuclear power plant design document. This multi-level mapping relationship closely links the design documents, the standard clause library, and the standard clauses.

[0131] In step 604 of some embodiments, the "reference association table" is a structured data table used to record the multi-level mapping relationship between nuclear power plant design documents and specification clauses. The table may contain multiple fields, such as design document number, design text fragment identifier, specification clause library identifier, text number, version number, clause number, and clause content. Storing the multi-level mapping relationship as a reference association table facilitates subsequent querying, tracing, and management.

[0132] Through steps 601 to 604, this embodiment achieves structured association and traceability between nuclear power plant design documents and specification clauses by constructing a multi-level mapping relationship and storing it as a reference association table. Specifically, the multi-level mapping relationship clearly shows the association path between design documents, the specification clause library, and specification clauses; the reference association table stores this association information in a structured form, facilitating subsequent querying, statistics, and analysis. This structured association method makes the specification reference information in design documents no longer fragmented, but easily traceable and manageable, providing convenience for the review, verification, and version control of design documents.

[0133] Please see Figure 7 In some embodiments, after step 604, steps 701 to 704 may be included, but are not limited to.

[0134] Step 701: Traverse the normalized clause information corresponding to all referenced clause information in the nuclear power plant design documents based on the reference association table.

[0135] Step 702: For each paradigm clause information, determine the corresponding normative clause library according to the second mapping relationship.

[0136] Step 703: Obtain the original clause information from the standard clause library and compare the paradigm clause information with the original clause information.

[0137] Step 704: When a difference is detected between the paradigm clause information and the original clause information, a difference location marker is generated and a content verification alarm is triggered.

[0138] In step 701 of some embodiments, "each record in the reference association table is accessed sequentially to obtain the normal form clause information corresponding to all referenced clauses in the nuclear power plant design documents. Since the reference association table stores multi-level mapping relationships between nuclear power plant design documents and standard clauses (including the first mapping relationship between design documents and the standard clause library, and the second mapping relationship between the standard clause library and standard clauses), all referenced normal form clause information can be obtained by traversal. For example, assuming there is a record in the reference association table indicating that design document A references clause C in the standard clause library B, then the traversal process will obtain the normal form clause information corresponding to clause C."

[0139] In step 702 of some embodiments, the "second mapping relationship" refers to the association between the normative clause library and the normative clauses, that is, which specific normative clauses are included in the normative clause library. Each normative clause information contains its source information (text number, version number, etc.). Based on this information and the second mapping relationship, the normative clause library to which the normative clause information belongs can be determined. For example, if the text number of a normative clause information is "GB-XXXX-2023" and the version number is "2023", according to the second mapping relationship, it can be determined that the normative clause information belongs to the normative clause library "GB-XXXX-2023".

[0140] In step 703 of some embodiments, "original clause information" refers to the original version of the specification clauses stored in the specification clause library without any modifications, which can be understood as the "standard answer". "Paradigm clause information" is the specification clause information extracted from the design documents and actually referenced by the designer, which can be understood as the "designer's answer". Comparing the "designer's answer" with the "standard answer" is to check whether the two are consistent.

[0141] In step 704 of some embodiments, when a difference is detected between the normative clause information and the original clause information, a difference location marker is generated and a content verification alarm is triggered. A "difference location marker" refers to marking the specific location in the normative clause information that differs from the original clause information, for example, using underlines, different colors, or highlighting to make the difference immediately apparent. Simultaneously, the system triggers a "content verification alarm," notifying relevant personnel (such as designers and quality control personnel) to conduct a verification. For example, if it is found that the content of a specification clause referenced in a design document is inconsistent with the original version in the specification clause library, the system will automatically mark the difference (e.g., underline the incorrectly referenced text in red) and send an email alarm to relevant personnel, reminding them to verify and correct it.

[0142] Steps 701 to 704, by traversing the reference association table, ensure that all referenced clauses are checked, achieving comprehensiveness in the inspection. By comparing the information of the normative clauses with the original clauses, issues such as reference errors and outdated versions can be identified, ensuring the accuracy of the inspection. Through difference location marking and content verification alarms, relevant personnel can be notified in a timely manner to handle the issues, avoiding design defects caused by incorrect references to the standard, and ensuring timely problem handling. This automated inspection mechanism improves the accuracy and reliability of standard references, reduces the risks caused by oversights in manual inspection, and provides a guarantee for the safe operation of nuclear power plants.

[0143] Please see Figure 8 In some embodiments, after step 604, steps 801 to 804 may also be included, but are not limited to.

[0144] Step 801: In response to the detection of an update to the text version number of the specification clause text, retrieve the revised clause information from the specification clause text.

[0145] Step 802: Based on the text number of the specification clause and the first mapping relationship, retrieve the nuclear power plant design documents from multiple design documents.

[0146] Step 803: Based on the revised clause information and the second mapping relationship, query the paradigm clause information corresponding to the revised clause information in the nuclear power plant design documents.

[0147] Step 804: Update the paradigm clause information based on the revised clause information.

[0148] In step 801 of some embodiments, once a change in the version number of a specification clause text is detected (e.g., from version 2022 to version 2023), the subsequent update process is immediately triggered. Differences between the old and new versions are automatically compared, and the differences are extracted as "revision clause information." For example, clauses added, deleted, or modified in the new version will be identified as revision clause information.

[0149] In step 802 of some embodiments, all design documents that reference the specification clause text can be found according to the first mapping relationship by using the text number of the specification clause text. For example, if the text number of the specification clause text is "GB-XXXX-2023", and both design document A and design document B reference the specification clause text "GB-XXXX-2023", then both design document A and design document B will be identified.

[0150] In step 803 of some embodiments, by revising the clause information (e.g., the modified clause content) and combining it with the second mapping relationship, the corresponding paradigm clause information can be found in the design document. That is, it is possible to find where in the design document these modified clauses are referenced. For example, if the revised clause information concerns a provision about a "safety valve," then all paradigm clause information referencing provisions related to "safety valves" will be searched in the design document.

[0151] In step 804 of some embodiments, the corresponding paradigmatic clause information in the design document is automatically modified according to the revised clause information to ensure that the design document is consistent with the latest specification clauses. For example, if the specification clauses regarding "safety valves" have changed, then all paradigmatic clause information in the design document that references "safety valves" will be automatically updated to be consistent with the new regulations.

[0152] Through steps 801 to 804, when the specification clauses change, the system can automatically identify, locate, and update all affected paradigm clause information in the design documents, ensuring that the design documents are always consistent with the latest specifications. This avoids design defects caused by outdated specifications, improves the quality and reliability of the design documents, significantly reduces the workload of manual updates, and increases work efficiency. This automated update mechanism is crucial for ensuring the safe operation of nuclear power plants.

[0153] Please see Figure 9 In some embodiments, after step 203, there may be steps including but not limited to step 901.

[0154] Step 901: Classify and label each paradigm clause information according to the preset classification rules to generate corresponding clause category labels.

[0155] In step 901 of some embodiments, the clause category label includes design compliance clauses, design reference clauses, and downstream execution clauses. "Preset classification rules" refer to a set of classification standards pre-established by domain experts based on factors such as the nature, purpose, and role of the specification clauses in the design process before system construction. These rules can be keyword-based, semantic-based, or rule engine-based. According to the preset classification rules, each paradigm clause information is analyzed and judged to determine its category. The clause category label is used to identify the category of the paradigm clause information. In this embodiment, the clause category label includes three types:

[0156] Design compliance clauses: These are mandatory provisions that must be strictly followed during the design process, directly affecting the safety, compliance, and functionality of the design. Examples include regulations regarding the selection of reactor pressure vessel materials and containment design pressure.

[0157] Design reference clauses: These clauses provide guidance or suggestions for the design, but are not mandatory. Designers can refer to these clauses, but can also adjust them according to specific circumstances. Examples include design suggestions for certain auxiliary systems, recommended calculation methods, etc.

[0158] Downstream implementation clauses: These clauses mainly target the construction, installation, commissioning, operation, and maintenance of nuclear power plants. They do not directly affect the design itself but need to be implemented in subsequent stages. Examples include regulations regarding equipment installation and requirements for operating procedures.

[0159] By categorizing and labeling the information in the normative clauses, we can manage the standard clauses more precisely, providing designers with clearer guidance. For example, during design reviews, we can focus on whether the "design compliance clauses" have been met; when optimizing the design, we can refer to the "design reference clauses" for improvement; and when preparing for construction, we can understand the requirements of the "downstream execution clauses" in advance. This categorized management approach improves the efficiency of utilizing the standard clauses, contributing to improved design quality and efficiency.

[0160] Please see Figure 10 In some embodiments, step 901 may include, but is not limited to, steps 1001 to 1004.

[0161] Step 1001: Perform mandatory compliance keyword matching on the paradigm clause information. When a successful match is detected between the paradigm clause information and the mandatory compliance keyword, mark the clause as a design compliance clause.

[0162] Step 1002: Perform suggested keyword matching on the paradigm clause information. When it is detected that the paradigm clause information matches the suggested keywords successfully and no mandatory compliance keyword matching is triggered, mark the clause as a design reference clause.

[0163] Step 1003: Perform execution instruction keyword matching on the paradigm clause information. When a successful match is detected between the paradigm clause information and the execution instruction keyword, mark the clause as a downstream execution clause.

[0164] Step 1004: Classify and statistically analyze the reference association table of the target design document according to the clause category label, and generate a reference distribution report including design compliance clauses, design reference clauses, and downstream execution clauses.

[0165] In step 1001 of some embodiments, mandatory compliance keywords are matched against the paradigm clause information. When a successful match is detected between the paradigm clause information and mandatory compliance keywords, the clause is marked as a design compliance clause. "Mandatory compliance keywords" refer to words or phrases that indicate mandatory compliance, such as "must," "must not," "prohibited," "mandatory," and "strictly comply." The system pre-establishes a mandatory compliance keyword database. By matching the paradigm clause information with keywords in the keyword database, if a match is successful, the clause is considered mandatory and falls under the category of "design compliance clauses." For example, if a paradigm clause contains the statement "Reactor pressure vessel materials must comply with XXX standards," then the clause will be marked as a "design compliance clause."

[0166] In some embodiments, determining mandatory nature does not rely solely on keyword matching, but is a multi-dimensional and comprehensive judgment process:

[0167] Prioritize assessing the mandatory level of the source document, first determining whether the regulatory or standard document to which the paradigm clause belongs is mandatory (e.g., laws, administrative regulations, mandatory national standards GB, etc.) or recommended (e.g., recommended national standards GB / T, industry recommended standards HG / T, etc.).

[0168] When examining the explicit mandatory statements in the clauses, check whether there is an official statement in the text of the regulations or standards (such as the preamble, general provisions, or specific chapters) that clearly indicates that the clause (or the chapter in which it is located) is mandatory.

[0169] Finally, perform mandatory feature word matching as in step 1001. A clause is marked as "design complies with the clause" when it meets the following conditions:

[0170] 1. It originates from mandatory regulations or standard documents;

[0171] 2. The document uses mandatory words (such as "prohibited" or "must") and the main text of the document does not explicitly exclude it from the scope of mandatory requirements; or, regardless of the nature of the document itself, the clause is explicitly declared as a mandatory clause in the main text of the document; or, it originates from a recommended standard document, but the clause is explicitly cited and required to be enforced by a higher-level mandatory document.

[0172] 3. Mandatory feature words were used.

[0173] It should be noted that if a clause is derived from a recommended regulation or standard document, and the document does not explicitly state that the clause is mandatory, then even if the clause uses seemingly mandatory words such as "must," it should not be marked as a "designed compliance clause" solely based on these words, because in this context, "should" may mean "strongly recommended" rather than legally mandatory.

[0174] In step 1002 of some embodiments, the paradigm clause information is matched with suggested keywords. When a successful match is detected between the paradigm clause information and suggested keywords, and no mandatory compliance keyword matching is triggered, the clause is marked as a design reference clause. "Suggested keywords" refer to words or phrases that express suggestion, recommendation, or reference, such as "suggest," "may," "suggest," "recommend," "reference," "usually," etc. The system pre-builds a suggested keyword database. If a paradigm clause information successfully matches suggested keywords but not mandatory compliance keywords (i.e., it does not belong to "design compliance clauses"), then the clause is considered a "design reference clause." For example, if a paradigm clause information contains a statement such as "It is recommended to use the XXX method for calculation," and the clause does not contain any mandatory keywords, then the clause will be marked as a "design reference clause."

[0175] In some embodiments, a clause is marked as a "Design Reference Clause" when it meets any of the following conditions:

[0176] The terms and conditions explicitly use suggestive keywords (such as "suggestive" or "allowed").

[0177] Based on the multi-dimensional comprehensive judgment in step 1001, this clause was not determined to be a "design compliance clause". This includes the aforementioned key exclusion cases, namely clauses that originate from recommended standards, have no explicit mandatory statements, but use mandatory wording.

[0178] For example, if a clause "recommends using the XXX method for calculation," it will be marked as a "design reference clause." Similarly, in the aforementioned example, "equipment layout must consider operational convenience" (derived from a GB / T standard without mandatory declarations) will be marked as a "design reference clause" in this step after it has not been determined to be mandatory according to step 1001.

[0179] In step 1003 of some embodiments, the explanatory clause information is matched with execution instruction keywords. When a successful match is detected between the explanatory clause information and the execution instruction keywords, the clause is marked as a downstream execution clause. "Execution instruction keywords" refer to words or phrases indicating operation, execution, or implementation, such as "installation," "debugging," "operation," "maintenance," "inspection," "should be performed in accordance with XXX procedure," etc. The system pre-establishes an execution instruction keyword database. If an explanatory clause information successfully matches an execution instruction keyword, the clause is considered a "downstream execution clause." For example, if an explanatory clause information contains the statement "Equipment installation should comply with XXX specification," then the clause will be marked as a "downstream execution clause."

[0180] In step 1004 of some embodiments, the reference association table of the target design document is classified and statistically analyzed according to the clause category tags to generate a reference distribution report containing design compliance clauses, design reference clauses, and downstream implementation clauses. The "reference association table" records the multi-level mapping relationship between the design document and the specification clauses, and each paradigm clause is tagged with a clause category tag. Statistical analysis of the reference association table reveals the number and proportion of references for each type of clause in the target design document, thus generating the "reference distribution report." This report visually demonstrates the degree of dependence of the design document on different types of specification clauses; for example, whether the reference ratio of design compliance clauses is sufficiently high, or whether any important mandatory clauses have been omitted.

[0181] Through steps 1001 to 1004, this embodiment of the application achieves automatic classification of normative clause information and generates a citation distribution report, providing a basis for the review and evaluation of design documents. Specifically, the keyword matching method is simple and efficient; the classification results can help designers quickly understand the nature and function of normative clauses; the citation distribution report can provide quantitative indicators for the quality assessment of design documents. For example, the proportion of citations of clauses that comply with the design can serve as an important indicator for assessing the compliance of design documents. This automated classification and statistical method improves the refinement of normative clause management and helps to improve design quality and efficiency.

[0182] The method for generating specification citation information for nuclear power plant design texts proposed in this application includes: acquiring multiple nuclear power plant design texts; determining a specification query text corresponding to each nuclear power plant design text; performing a clause query in a pre-built specification clause library based on the specification query text to obtain the reference clause information matching the specification query text; wherein the specification clause library performs a clause update operation once every preset period; and generating citation information matching the nuclear power plant design text based on the reference clause information corresponding to the specification query text.

[0183] This application acquires multiple nuclear power plant design documents, identifies a corresponding specification query text for each document, extracts key information from each design document, and further searches a pre-built specification clause library based on the specification query text to obtain matching reference clause information, thus achieving automatic association between design documents and specification clauses. Specifically, the specification clause library is updated every preset period to ensure its timeliness and accuracy, avoiding citation errors due to outdated specification clauses. Finally, based on the reference clause information corresponding to the specification query text, citation information matching the nuclear power plant design documents is generated, providing designers with clear and accurate specification references. Compared to existing technologies that rely on manual annotation or static database retrieval, the method provided in this application achieves dynamic association between design documents and specification clauses through automated text processing and clause matching, avoiding omissions or misuse problems in the manual search and matching process. In summary, this application can achieve efficient citation association between nuclear power plant design documents and standard clauses, reducing human error.

[0184] Please see Figure 11 , Figure 11 This is a schematic diagram illustrating the framework of a management system for the application and management of regulatory and standard provisions in nuclear power plant design, provided as an embodiment of this application. The system mainly comprises three parts: structuring of regulatory and standard provisions, application implementation, and structuring of design outcomes.

[0185] The structured part of the regulations and standards clauses, as input to the system, decomposes multiple technical standards (i.e., normative clause texts) and extracts specific clauses (clause 1, clause 2, etc.) from each standard. Each normative clause text contains multiple clauses.

[0186] In the application implementation section, iterative data processing enables a many-to-many mapping between regulatory and standard clauses and design clauses. Specifically, regulatory and standard clauses are divided into three categories: design compliance clauses, design reference clauses, and downstream implementation clauses. "Design compliance clauses" are mandatory clauses that must be strictly followed during the design process; "design reference clauses" are non-mandatory clauses that provide guidance or advice for the design; and "downstream implementation clauses" are clauses that guide downstream stages such as the construction, installation, commissioning, operation, and maintenance of nuclear power plants. The document preparation module utilizes structured clause information to provide functions such as real-time querying, automatic referencing, clause summarization, and verification, supporting the generation and management of design documents.

[0187] The structured portion of the design deliverables, based on the processing results of the application implementation portion, presents the design deliverables in a structured manner according to the design compliance clauses, design reference clauses, and downstream execution clauses, ensuring that the design deliverables meet the requirements of regulations and standards.

[0188] In addition, the system includes data transmission and external interfaces. The data transmission module transmits structured terms and conditions to downstream inputs, which may then be manually supplemented or adjusted. The external interface outputs processed information to guide downstream operations and ultimately generate downstream work results. The system also provides query and export functions, allowing users to query and export relevant data from the system.

[0189] Please see Figure 12 This application also provides an apparatus for generating specification citation information for nuclear power plant design texts, which can implement the above-mentioned method for generating specification citation information for nuclear power plant design texts, including:

[0190] The acquisition module is used to acquire design documents for multiple nuclear power plants;

[0191] The determination module is used to determine the specification query text corresponding to each nuclear power plant design text.

[0192] The query module is used to perform clause queries in a pre-built standard clause library based on the standard query text to obtain reference clause information that matches the standard query text; wherein, the standard clause library performs a clause update operation once every preset period;

[0193] The generation module is used to generate citation information that matches the nuclear power plant design text based on the reference clause information corresponding to the reference text in the specification query text.

[0194] Please see Figure 13 , Figure 13 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0195] The processor 1301 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0196] The memory 1302 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 1302 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1302, and the processor 1301 calls and executes the specification citation information generation method for nuclear power plant design texts according to the embodiments of this application.

[0197] The input / output interface 1303 is used to implement information input and output;

[0198] The communication interface 1304 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0199] Bus 1305 transmits information between various components of the device (e.g., processor 1301, memory 1302, input / output interface 1303, and communication interface 1304);

[0200] The processor 1301, memory 1302, input / output interface 1303 and communication interface 1304 are connected to each other within the device via bus 1305.

[0201] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for generating specification citation information for nuclear power plant design texts.

[0202] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0203] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0204] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0205] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0206] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0207] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0208] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0209] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0210] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0211] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0212] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0213] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for generating specification citation information for nuclear power plant design texts, characterized in that, include: Obtain design documents for multiple nuclear power plants; For each of the aforementioned nuclear power plant design documents, determine the corresponding specification query text for that nuclear power plant design document; Based on the specified query text, a clause search is performed in a pre-built specification clause library to obtain the referenced clause information matching the specified query text; wherein, the specification clause library performs a clause update operation every preset period; the pre-construction process of the specification clause library includes: acquiring multiple specification clause texts; performing text recognition on each specification clause text to extract multiple specification clauses and text attribute information for each specification clause text; the text attribute information includes text number and text version number; for each specification clause, constructing paradigm clause information based on the text attribute information corresponding to the specification clause text to which the specification clause belongs; constructing the specification clause library based on the multiple paradigm clause information; Based on the cited clause information corresponding to the query text in the specification, citation information matching the nuclear power plant design text is generated. After generating the citation information, the method further includes: generating a nuclear power plant design document based on each nuclear power plant design document and the corresponding citation information; parsing all citation information in the nuclear power plant design document to obtain the text attribute information and the specification clause corresponding to each citation information; constructing a multi-level mapping relationship between the nuclear power plant design document and the specification clause library based on the text attribute information corresponding to each specification clause; wherein, the multi-level mapping relationship includes a first mapping between the nuclear power plant design document and the specification clause library. The system establishes a relationship between the standard clause library and the standard clauses, and a second mapping relationship between them; it stores the multi-level mapping relationship as a reference association table in the form of a structured table; in response to detecting an update in the text version number of the standard clause text, it queries the standard clause text to obtain the revised clause information; based on the text number of the standard clause text and the first mapping relationship, it queries multiple design documents to obtain the nuclear power plant design documents; based on the revised clause information and the second mapping relationship, it queries the nuclear power plant design documents to obtain the paradigm clause information corresponding to the revised clause information; and it updates the paradigm clause information based on the revised clause information.

2. The method for generating specification citation information for nuclear power plant design texts according to claim 1, characterized in that, The step of performing a clause search in a pre-built standard clause library based on the standard query text to obtain reference clause information matching the standard query text includes: Based on the specified query text, a fuzzy search and matching is performed on multiple paradigm clause information to determine multiple candidate paradigm clause information; Calculate the relevance score between each candidate paradigm clause and the normative query text; Based on the relevance score, the information of multiple candidate paradigm clauses is sorted to obtain and display a list of candidate paradigm clause information. In response to a selection operation for the candidate paradigm clause information list, the reference clause information matching the specification query text is determined based on the selection operation.

3. The method for generating specification citation information for nuclear power plant design texts according to claim 2, characterized in that, The calculation of the relevance score between each candidate paradigm clause and the canonical query text includes: Obtain the number of keyword matches between each candidate paradigm clause and the standard query text; The relevance score of the candidate paradigm clause information is calculated based on the number of keyword matches.

4. The method for generating specification citation information for nuclear power plant design texts according to claim 2, characterized in that, The process of sorting multiple candidate paradigm clause information based on the relevance score to obtain and display a list of candidate paradigm clause information includes: The candidate paradigm clause information is sorted based on the relevance score; The candidate paradigm clauses are displayed in descending order of relevance score, and the matching fields that successfully match the normative query text are highlighted.

5. The method for generating specification citation information for nuclear power plant design texts according to claim 1, characterized in that, After storing the multi-level mapping relationship as a reference association table in structured table form, the method further includes: Based on the reference association table, traverse the normal form clause information corresponding to all referenced clause information in the nuclear power plant design document; For each of the aforementioned paradigm clauses, the corresponding normative clause library is determined according to the second mapping relationship; Obtain the original clause information from the standard clause library, and compare the paradigm clause information with the original clause information; When a difference is detected between the paradigm clause information and the original clause information, a difference location marker is generated and a content verification alarm is triggered.

6. The method for generating specification citation information for nuclear power plant design texts according to claim 1, characterized in that, After constructing paradigm clause information for each of the aforementioned normative clauses based on the text attribute information corresponding to the normative clause text to which the normative clause belongs, the method further includes: Each of the aforementioned paradigm clauses is categorized and labeled according to a preset classification rule, generating a corresponding clause category label; wherein, the clause category label includes design compliance clauses, design reference clauses, and downstream execution clauses.

7. The method for generating specification citation information for nuclear power plant design texts according to claim 6, characterized in that, The step of classifying and labeling each of the paradigm clauses according to a preset classification rule includes: The paradigm clause information is subjected to mandatory compliance keyword matching. When the paradigm clause information is successfully matched with the mandatory compliance keyword, the clause is marked as a design compliance clause. The paradigm clause information is matched with suggested keywords. When the paradigm clause information is successfully matched with the suggested keywords and no mandatory compliance keyword matching is triggered, the clause is marked as a design reference clause. The paradigm clause information is matched with execution instruction keywords. When a successful match is detected between the paradigm clause information and the execution instruction keywords, the clause is marked as a downstream execution clause. Based on the aforementioned clause category labels, the reference association table of the target design document is categorized and statistically analyzed to generate a reference distribution report containing the aforementioned design compliance clauses, design reference clauses, and downstream execution clauses.

8. A device for generating specification citation information for nuclear power plant design texts, characterized in that, include: The acquisition module is used to acquire design documents for multiple nuclear power plants; The determination module is used to determine the specification query text corresponding to each nuclear power plant design text. A query module is used to perform clause queries in a pre-built standard clause library based on the standard query text to obtain reference clause information matching the standard query text; wherein, the standard clause library performs a clause update operation every preset period; the pre-construction process of the standard clause library includes: acquiring multiple standard clause texts; performing text recognition on each standard clause text to extract multiple standard clauses and text attribute information for each standard clause text; the text attribute information includes a text number and a text version number; for each standard clause, constructing paradigm clause information based on the text attribute information corresponding to the standard clause and the standard clause text to which the standard clause belongs; and constructing the standard clause library based on the multiple paradigm clause information. The generation module is used to generate citation information matching the nuclear power plant design text based on the citation clause information corresponding to the specification query text. After generating the citation information, the module further includes: generating a nuclear power plant design document based on each nuclear power plant design text and the corresponding citation information; parsing all citation information in the nuclear power plant design document to obtain the text attribute information and specification clauses corresponding to each citation information; and constructing a multi-level mapping relationship between the nuclear power plant design document and the specification clause library based on the text attribute information corresponding to each specification clause. The multi-level mapping relationship includes the first level of the mapping relationship between the nuclear power plant design document and the specification clause library. A mapping relationship is established, and a second mapping relationship is established between the standard clause library and the standard clauses; the multi-level mapping relationship is stored as a reference association table in the form of a structured table; in response to detecting an update of the text version number of the standard clause text, the revised clause information is retrieved from the standard clause text; the nuclear power plant design document is retrieved from multiple design documents according to the text number of the standard clause text and the first mapping relationship; the paradigm clause information corresponding to the revised clause information is retrieved from the nuclear power plant design document according to the revised clause information and the second mapping relationship; the paradigm clause information is updated according to the revised clause information.

9. An electronic device, characterized in that, include: The device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for generating specification citation information for nuclear power plant design texts as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method for generating specification citation information for nuclear power plant design texts as described in any one of claims 1 to 7.

Images