Industrial specification text processing method, computer equipment and medium
Through the neural network model, design objects and constraints are extracted from industry standard texts, rule condition statements are generated and a rule library is constructed. This solves the problem that industry standard texts are difficult to convert into design tool judgments, realizes real-time constraints and error correction in the design process, and improves the efficiency of design scheme generation.
Patent Information
- Application Number
- CN202510752514.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-06
- Publication Date
- 2025-09-12
AI Technical Summary
In the existing technology, it is difficult to convert industry specification texts into judgment programs that can be executed by design tools, which makes designers prone to errors during the design process and the efficiency of generating qualified design solutions is low.
Through the neural network model, the design objects, design attributes and design constraints in the industry specification text are extracted, rule condition statements are generated and a rule library is built to achieve real-time constraints and error correction of design schemes.
It improves the efficiency of designers in using industry standard texts, reduces design errors, and reduces rework costs and compliance risks.
Smart Images
Figure CN120633419A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of industry standard texts, and in particular to a method, computer equipment, and medium for processing industry standard texts. Background Art
[0002] In industries like architectural design and industrial manufacturing, designers must strictly adhere to numerous industry standards and regulations. These standards often consist of hundreds of pages of text, covering complex terms such as size restrictions, material selection, and spatial layout. In practice, designers often need to review documents and check design parameters simultaneously, and even the slightest mistake can lead to design violations. For example, details such as the reserved dimensions for fire escape corners and the location of openings in load-bearing walls are easily overlooked by even experienced designers.
[0003] It can be seen that the current industry standard texts are not conducive to designers' use and verification, resulting in low efficiency in generating qualified design solutions. Summary of the Invention
[0004] The embodiments of the present application provide a method, computer equipment, and medium for processing industry standard texts, aiming to facilitate designers' use and verification of industry standard texts, thereby improving the efficiency of generating qualified design solutions.
[0005] In a first aspect, an embodiment of the present application provides a method for processing an industry standard text, the method comprising:
[0006] Obtain unstructured industry specification text;
[0007] Using a neural network model, extracting design objects, design attributes, and design constraints from the industry specification text;
[0008] generating corresponding rule condition statements based on the design object, the design attributes, and the design constraint conditions;
[0009] The rule conditional statements are used to generate a rule base of industry standard texts, and the rule base is used to constrain the design solution.
[0010] In some embodiments, the unstructured industry specification text includes multiple industry specification clauses, and the extracting of design objects, design attributes, and design constraints from the industry specification text using a neural network model includes:
[0011] Determining boundaries between adjacent industry specification clauses in the unstructured industry specification text using a clause segmentation model;
[0012] According to the boundary, determining a plurality of the industry specification clauses in the unstructured industry specification text;
[0013] Named entity recognition is performed on each of the industry specification clauses to obtain the design object, the design attribute, and the design constraint condition in the industry specification clause.
[0014] In some embodiments, generating corresponding rule condition statements based on the design object, the design attributes, and the design constraints includes:
[0015] For the design object, the design attribute and the design constraint in each of the industry specification clauses, a rule condition statement of the industry specification clause is generated, and the rule condition statement records that the design attribute of the design object needs to meet the design constraint.
[0016] In some embodiments, before generating the rule condition statement of the industry specification clause for the design object, the design attribute, and the design constraint in each industry specification clause, the method further includes:
[0017] Performing fuzzy expression conversion processing on the design object, the design attribute, and the design constraint in each of the industry specification clauses to replace at least one fuzzy expression term in the design object, the design attribute, and the design constraint;
[0018] A rule condition statement of the industry specification clause is generated using at least one of the replaced design object, the design attribute, and the design constraint condition.
[0019] In some embodiments, after generating the rule conditional statement of the industry specification clause, the method further includes:
[0020] Performing natural language classification on the industry specification clauses to determine a clause validity type of the industry specification clauses, where the clause validity type includes at least one of a mandatory clause, a recommended clause, and an explanatory clause;
[0021] A rule condition statement that associates the clause effectiveness type with the industry specification clause.
[0022] In some embodiments, after generating a rule base of industry standard text using the rule conditional statements, the method further includes:
[0023] Obtaining operation events for design solutions in target design software;
[0024] Determine the operation object, operation attributes, and values of the operation attributes pointed to by the operation event;
[0025] Using the rule conditional statements of the rule base, the operation object, and the operation attribute, a rule check is performed on the value of the operation attribute to obtain a check result;
[0026] If the inspection result is failure, output inspection result prompt information of the value of the operation attribute.
[0027] In some embodiments, after performing rule checking on the value of the operation attribute and obtaining the check result, the method further includes:
[0028] If the test result is that the test fails, obtaining the target rule conditional statement that fails the test in the rule base;
[0029] Determining a target clause validity type associated with the target rule conditional statement, where the target clause validity type includes at least one of a mandatory clause, a recommended clause, and an explanatory clause;
[0030] Output prompt information of the effectiveness type of the target clause.
[0031] In some embodiments, after obtaining the target rule conditional statement that fails the test in the rule base, the method further includes:
[0032] Determining target design constraints in the target rule conditional statement;
[0033] According to the target design constraint conditions, correction suggestion information of the value of the operation attribute is output.
[0034] In a second aspect, an embodiment of the present application provides a device for processing an industry standard text, the device comprising:
[0035] Acquisition module, used to obtain unstructured industry specification text;
[0036] An extraction module, configured to extract design objects, design attributes, and design constraints from the industry specification text using a neural network model;
[0037] A first generating module, configured to generate corresponding rule condition statements based on the design object, the design attributes, and the design constraint conditions;
[0038] The second generating module is used to generate a rule base of industry standard text using the rule conditional statements, and the rule base is used to constrain the design solution.
[0039] In a third aspect, an embodiment of the present application provides a computer device comprising a processor and a memory, wherein a computer program is stored in the memory, and the computer program is configured to be executed by the processor to implement a method for processing an industry standard text as described in any one of the above items.
[0040] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, wherein the computer program is configured to be executed by a processor to implement a method for processing an industry specification text as described in any one of the above items.
[0041] In a fifth aspect, an embodiment of the present application provides a computer program product, including a computer program or instructions, which are executed by a processor to implement a method for processing industry standard texts as described in any of the above items.
[0042] Beneficial effects of the embodiments of the present application:
[0043] In an embodiment of the present application, a neural network model is used to extract design objects, design attributes, and design constraints from industry specification texts, and then generate corresponding rule condition statements and a rule base of the industry specification text, thereby converting the unstructured industry specification text into a structured rule base. Compared with designers flipping through documents and checking design parameters at the same time, the structured rule base is more conducive to designers' use and verification, thereby improving the efficiency of generating qualified design solutions. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0045] Figure 1 This is a flowchart of an embodiment of a method for processing industry standard texts provided in an embodiment of the present application;
[0046] Figure 2 This is a flowchart of another embodiment of a method for processing industry standard texts provided in an embodiment of the present application;
[0047] Figure 3 This is a flowchart of another embodiment of the method for processing industry standard texts provided in the embodiments of the present application;
[0048] Figure 4 This is a flowchart of another embodiment of the method for processing industry standard texts provided in the embodiments of the present application;
[0049] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0050] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.
[0051] In the description of this application, "plurality" means two or more, unless otherwise specifically defined. Furthermore, in the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features being described. Thus, features defined as "first" or "second" may explicitly or implicitly include one or more of the described features.
[0052] In the related art, manual methods can be used to verify the design plan using unstructured industry standard texts, but this method relies on the designer's memory and understanding of unstructured industry standard texts, which is inefficient and prone to errors. When the design plan is complex, it often needs to be submitted for review repeatedly, and it takes several days to discover errors, resulting in high rework costs. Although related design software (such as AutoCAD) supports preset design dimension constraints, the constraints need to be manually coded and input, and cannot automatically adapt to specification updates. The development cycle is long and the cost is high, and the specification library update is delayed. Professional review tools (such as BIM (Building Information Modeling) compliance detection systems) can usually only perform batch checks after the design is completed and cannot intervene in the operation process in real time. During the designer modeling stage in the related design software, potential non-compliant designs cannot be perceived, and its rule base also needs to be manually entered, and the rule base update cost is high and the update is delayed.
[0053] It can be seen that the core of these defects lies in the fact that unstructured specification texts are difficult to convert into judgment procedures that can be executed by design tools, and the separation of design tools and review processes causes serious delays in error feedback.
[0054] Based on this, the present invention provides a comprehensive solution, from parsing unstructured industry specification texts to dynamically enforcing rules and providing real-time error correction feedback. This solution enables "operation-as-review" during the design process, reducing compliance risks and rework costs. For a more detailed description of the solution, please refer to the following.
[0055] In the first aspect, the embodiments of the present application provide a method for processing industry standard texts. Specifically, referring to Figure 1 , Figure 1 The following is a flow chart of an embodiment of a method for processing industry standard texts. Figure 1 The processing methods for the industry standard text may include:
[0056] 101. Obtain unstructured industry specification text.
[0057] In the embodiments of this application, industry specification text refers to text used to describe industry specifications, such as the "Code for Fire Protection Design of Buildings" and the "Standard for Electrical Design of Civil Buildings." Industry specification text is usually unstructured, that is, it is described in natural language and does not have a fixed format.
[0058] In some embodiments of the present application, unstructured industry standard text can be obtained by inputting industry standard files in any modality, for example, by inputting industry standard files in various formats such as paper document scans, PDF, and Word. For paper document scans, an OCR (Optical Character Recognition) model can be used to recognize the text content therein to obtain the corresponding unstructured industry standard text. The OCR model can be, for example, a model such as Paddle OCR.
[0059] 102. Use neural network models to extract design objects, design attributes and design constraints from industry specification texts.
[0060] In an embodiment of the present application, an industry specification text may include a set of related design objects, design attributes, and design constraints. For example, in the architectural design industry, if the industry specification text includes "the clear width of an evacuation staircase should not be less than 1.1 meters," then the corresponding design object may be the evacuation staircase, the corresponding design attribute may be the clear width, and the corresponding design constraint may be "not less than 1.1 meters." The design objects, design attributes, and design constraints may be extracted from the industry specification text using a corresponding neural network model. The neural network model may be obtained through prior training.
[0061] 103. Generate corresponding rule conditional statements based on design objects, design attributes and design constraints.
[0062] In the embodiments of the present application, a rule conditional statement refers to a conditional statement that represents a corresponding rule, such as an IF-THEN conditional statement in a computer programming language, where the steps after THEN are executed when the condition after IF is met. By generating rule conditional statements, it is possible to more conveniently use and verify the corresponding industry standard text.
[0063] 104. Use rule conditional statements to generate a rule base of industry standard text, which is used to constrain design solutions.
[0064] In an embodiment of the present application, since the industry specification text usually includes multiple groups of design objects, design attributes and design constraints that have an associated relationship, the multiple groups of design objects, design attributes and design constraints can generate corresponding rule condition statements. Therefore, the multiple groups of rule condition statements can be summarized to obtain a rule base of the industry specification text, which can be used to subsequently constrain the designer's design plan.
[0065] In some embodiments of the present application, a rule base for industry specification texts can be implemented based on a graph database (e.g., Neo4j). Specifically, generating a rule base for industry specification texts using rule conditional statements can include converting the rule conditional statements into a database format, establishing object nodes (i.e., nodes where design objects are located), rule nodes (i.e., nodes where rule conditional statements are located), associations between rules and objects, and dependencies between different rules in the graph database, thereby obtaining a rule base in the form of a graph database.
[0066] In some embodiments of the present application, the rule nodes in the graph database may be exemplified as follows:
[0067] / / Rule node (including the above design properties)
[0068] CREATE(:Rule{
[0069] id:"R001",
[0070] name:"Fire escape width",
[0071] effect: "Forced",
[0072] version:"GB50016-2023",
[0073] condition: "object.type='fire stairs' AND width<1.1",
[0074] action: "Throw violation"
[0075] });
[0076] In some embodiments of the present application, the object nodes in the graph database may be exemplified as follows:
[0077] / / Object node
[0078] CREATE(:ObjectType{name:"fire escape stairs"});
[0079] In some embodiments of the present application, the association relationship between rules and objects in the graph database can be exemplified as follows:
[0080] / / Establish the relationship between rules and objects
[0081] MATCH(r:Rule{id:"R001"}),(o:ObjectType{name:"fire escape stairs"})
[0082] CREATE(r)-[:APPLIES_TO]->(o);
[0083] In some embodiments of the present application, the dependency relationship between different rules in the graph database can be exemplified as follows:
[0084] / / Dependencies between different rules
[0085] MATCH(r1:Rule{id:"R001"}),(r2:Rule{id:"R002"})
[0086] CREATE(r1)-[:DEPENDS_ON]->(r2);
[0087] It can be seen that in the above-mentioned embodiments of the present application, the design objects, design attributes and design constraints in the industry specification text are extracted through the neural network model, and the corresponding rule condition statements and the rule base of the industry specification text are generated, thereby converting the unstructured industry specification text into a structured rule base. Compared with designers flipping through documents and checking design parameters at the same time, the structured rule base is more conducive to designers' use and verification, thereby improving the efficiency of generating qualified design solutions.
[0088] In some embodiments of the present application, Figure 2 As shown, in Figure 1 Based on the illustrated embodiment, the unstructured industry specification text includes multiple industry specification clauses arranged in sequence, such as the first industry specification clause, the second industry specification clause, the third industry specification clause, etc. Each industry specification clause may include at least one set of design objects, design attributes, and design constraints that are associated with each other. Accordingly, using a neural network model to extract design objects, design attributes, and design constraints from the industry specification text may include:
[0089] 201. Use the clause segmentation model to determine the boundaries of adjacent industry specification clauses in unstructured industry specification texts.
[0090] In an embodiment of the present application, the neural network model may include a clause segmentation model, which refers to a model for segmenting multiple industry specification clauses in an unstructured industry specification text. Specifically, the clause segmentation model can be used to identify boundaries between adjacent industry specification clauses in the unstructured industry specification text.
[0091] In some embodiments of the present application, the clause segmentation model may adopt a pre-trained BiLSTM-CRF model, for example. The BiLSTM-CRF model is a deep learning model that combines a bidirectional long short-term memory network (BiLSTM) and a conditional random field (CRF). The model captures the contextual information of the input sequence through BiLSTM, generates an emission score, and then considers the transfer relationship between labels through CRF to calculate the path score, thereby making a more accurate prediction. The model training data of the clause segmentation model may include the labeled data of more than 200 industry specifications such as the "Code for Fire Protection Design of Buildings".
[0092] 202. According to the boundaries, identify multiple industry standard clauses in the unstructured industry standard text.
[0093] In an embodiment of the present application, after determining the boundaries of adjacent industry specification clauses in an unstructured industry specification text, the adjacent industry specification clauses can be divided according to the boundaries to obtain multiple industry specification clauses in the unstructured industry specification text.
[0094] 203. Perform named entity recognition on each industry specification clause to obtain the design objects, design attributes and design constraints in the industry specification clause.
[0095] In the embodiments of the present application, named entity recognition (NER) refers to identifying entities with specific meanings in text, such as design objects, design attributes, and design constraints in industry specification clauses.
[0096] In some embodiments of the present application, named entity recognition can be implemented using a neural network model. For example, a BERT (Bidirectional Encoder Representation from Transformers) model can be used. The BERT model is fine-tuned based on the industry in which the industry specification text is located to obtain a model that can be used to identify design objects, design attributes, and design constraints in industry specification clauses.
[0097] In some embodiments of the present application, when an unstructured industry specification text includes multiple industry specification clauses arranged in sequence, generating corresponding rule conditional statements based on design objects, design attributes, and design constraints may include: generating a rule conditional statement for each industry specification clause for the design object, design attribute, and design constraint in each industry specification clause. The rule conditional statement records that the design attribute of the design object must satisfy the design constraint.
[0098] In some embodiments of the present application, the generation of rule conditional statements can also be implemented based on a neural network model. For example, the QwQ-32B large language model can be used and fine-tuned based on the industry in which the industry specification text is located to obtain a model that can be used to convert design objects, design attributes, and design constraints into corresponding rule conditional statements. For example, taking the design object as an evacuation staircase, the design attribute as the clear width, and the design constraint as not less than 1.1 meters, the corresponding rule conditional statement can be, for example, "IF object = evacuation staircase AND object.clear width < 1.1m THEN violation."
[0099] In some embodiments of the present application, since the descriptions of some industry specification clauses are relatively vague, they can be pre-processed before generating the rule conditional statements. Specifically, for the design objects, design attributes, and design constraints in each industry specification clause, before generating the rule conditional statements of the industry specification clause, the following can also be included: for the design objects, design attributes, and design constraints in each industry specification clause, fuzzy expression conversion processing is performed to replace at least one fuzzy expression word in the design object, design attribute, and design constraint; and the rule conditional statements of the industry specification clause are generated using at least one of the replaced design objects, design attributes, and design constraints. Taking the industry specification clause "Evacuation passages should avoid sharp angle turns" as an example, the design object is the evacuation passage, the design attribute is the turn, and the design constraint is to avoid sharp angles. Then, the replaced design attribute can be the turn angle, and the replaced design constraint can be less than 90 degrees. The rule conditional statement generated based on this can be "IF object = evacuation passage AND object.turn angle < 90° THEN violation", so that the generation of the rule conditional statement supports fuzzy expression conversion. The fuzzy expression conversion processing can be achieved through natural language processing (NLP).
[0100] In some embodiments of the present application, since some of the industry specification clauses are mandatory clauses, some are recommended clauses, and some are explanatory clauses, the industry specification conditions can also be classified according to the effectiveness of the clauses. Specifically, after generating the rule conditional statements of the industry specification clauses, it can also include: natural language classification of the industry specification clauses to determine the clause effectiveness type of the industry specification clauses, the clause effectiveness type includes at least one of mandatory clauses, recommended clauses, and explanatory clauses; associating the clause effectiveness type with the rule conditional statements of the industry specification clauses, so that subsequent designers can determine the effectiveness of the corresponding industry specification clauses based on the clause effectiveness type. Among them, the clause effectiveness type can be determined based on keywords in the industry specification clauses, such as recommended, best, prohibited, must not, and must.
[0101] In some embodiments of the present application, Figure 3 As shown, in Figure 1 or Figure 2 Based on the embodiment shown, after generating a rule base of industry standard text using rule conditional statements, the following steps may also be included:
[0102] 301. Obtain an operation event for a design solution in a target design software.
[0103] In an embodiment of the present application, the target design software may be, for example, CAD (Autodesk Computer Aided Design) software, BIM (Building Information Modeling) software, etc., and BIM software may include, for example, Revit software. A user may generate a design plan in the target design software. Operation events for the design plan are triggered by the user and can be monitored through the API interface of the target design software. Operation events for the design plan may include, for example: object creation / deletion, attribute modification (such as size, position), topological relationship changes (such as connection to other components), etc. in the architectural design plan.
[0104] 302. Determine the operation object, operation attributes, and values of the operation attributes pointed to by the operation event.
[0105] In an embodiment of the present application, the operation object pointed to by the operation event may be, for example, the design object that the user wants to operate in the architectural design plan, the operation attribute pointed to by the operation event may be, for example, the design attribute of the design object that the user wants to operate in the architectural design plan, and the value of the operation attribute pointed to by the operation event may be, for example, the value of the design attribute of the design object that the user wants to operate in the architectural design plan.
[0106] 303. Using the rule condition statements, operation objects, and operation attributes of the rule base, rule verification is performed on the values of the operation attributes to obtain verification results.
[0107] In the embodiment of the present application, since there are multiple rule conditional statements in the rule base, the target rule statement with the operation object and the operation attribute is screened out from the multiple rule conditional statements in the rule base, and then the target rule statement is used to perform rule verification on the value of the operation attribute to obtain the verification result, thereby detecting the design compliance in real time during the user operation process and providing dynamic feedback. The verification result may include at least one of the following: pass, fail, etc.
[0108] In some embodiments of the present application, the step of performing rule verification on the value of the operation attribute using the target rule statement may include: verifying whether the value of the operation attribute satisfies the target design constraint conditions in the target rule statement; if the value of the operation attribute satisfies the target design constraint conditions in the target rule statement, determining that the verification result is passed; if the value of the operation attribute does not satisfy the target design constraint conditions in the target rule statement, determining that the verification result is failed.
[0109] 304. If the inspection result is failure, output inspection result prompt information of the value of the operation attribute.
[0110] In an embodiment of the present application, if the inspection result is a failure, indicating that the value of the operation attribute is not appropriate, a prompt message indicating the inspection result of the operation attribute value is output. For example, the prompt message indicating the inspection result of the operation attribute value can be displayed by overlaying the interface of the target design software to prompt the corresponding user. The prompt message indicating the inspection result of the operation attribute value can include at least one of the operation object, the operation attribute, the value of the operation attribute, and the target rule statement.
[0111] In some embodiments of the present application, Figure 4 As shown, in Figures 1 to 3 Based on any of the embodiments shown, after performing rule verification on the values of the operation attributes and obtaining the verification results, the following steps may also be performed:
[0112] 401. If the test result is failure, obtain the target rule conditional statement that failed the test in the rule base.
[0113] In an embodiment of the present application, if the test result is that the test fails, the rule conditional statement with the above-mentioned operation object and operation attribute in the rule base can be used as the target rule conditional statement that fails the test in the rule base.
[0114] 402. Determine a target clause validity type associated with a target rule conditional statement, where the target clause validity type includes at least one of a mandatory clause, a recommended clause, and an explanatory clause.
[0115] In the embodiment of the present application, since each rule conditional statement in the rule base is associated with a corresponding clause effectiveness type, the target clause effectiveness type associated with the target rule conditional statement can be determined.
[0116] In some embodiments of the present application, after determining the target clause effectiveness type associated with the target rule conditional statement, it may also include: if the target clause effectiveness type is a mandatory clause, then executing the step of outputting the inspection result prompt information of the value of the operation attribute, so that the user can modify the value of the operation attribute based on the inspection result prompt information; if the target clause effectiveness type is not a mandatory clause, but a recommended clause or an explanatory clause, then the step of outputting the inspection result prompt information of the value of the operation attribute may not be executed, so as to avoid causing excessive interference to the user's operations in the target design software.
[0117] 403. Output prompt information of the effectiveness type of the target clause.
[0118] In an embodiment of the present application, the prompt information of the target clause effectiveness type may include the display color of the prompt information of the inspection result of the value of the operation attribute, that is, the prompt information of the target clause effectiveness type is reflected in the corresponding display color. Taking the target clause effectiveness type as a mandatory clause as an example, the display color of the prompt information of the inspection result of the value of the operation attribute can be red, taking the target clause effectiveness type as a recommended clause as an example, the display color of the prompt information of the inspection result of the value of the operation attribute can be yellow, taking the target clause effectiveness type as an explanatory clause as an example, the display color of the prompt information of the inspection result of the value of the operation attribute can be blue, so as to facilitate the user to identify the target clause effectiveness type of the target rule condition.
[0119] In addition, when the user hovers the mouse over the inspection result prompt information of the value of the operation attribute, the inspection details can also be displayed. The displayed inspection details may include, for example, the industry specification clauses used to generate the target rule conditional statement, the value of the operation attribute, the target design constraint conditions in the target rule statement, and at least one of the correction suggestion information of the value of the operation attribute.
[0120] In some embodiments of the present application, after obtaining a target rule conditional statement that failed the inspection in the rule library, the following may also be included: determining the target design constraint condition in the target rule conditional statement; and outputting correction suggestion information for the value of the operation attribute according to the target design constraint condition. For example, a value that satisfies the target design constraint condition and has the smallest difference with the value of the operation attribute may be used as the recommended value for the operation attribute. The correction suggestion information may include the recommended value for the operation attribute. The correction suggestion information for the value of the operation attribute may be output in a display of inspection details.
[0121] In some embodiments of the present application, a one-click correction function for the value of an operational attribute is also provided. Specifically, a user can click on the output correction suggestion information for the value of the operational attribute to trigger an instruction to correct the value of the operational attribute; in response to the correction instruction, the value of the operational attribute is replaced with the suggested value of the operational attribute, thereby realizing the one-click correction function for the value of the operational attribute.
[0122] In some embodiments of the present application, after a rule check is performed on the value of the operation attribute and the check result is obtained, it may also include: if the check result is a check failure, obtaining the target rule conditional statement that failed the check in the rule base; based on the target rule conditional statement that failed the check in the rule base, counting the cumulative number of times each rule conditional statement in the rule base fails the check; according to the cumulative number, determining a plurality of rule conditional statements to be output whose cumulative number is greater than a preset number threshold among the multiple rule conditional statements in the rule base, and then determining a target number of multiple rule conditional statements to be output whose cumulative number is greater than the preset number threshold; sorting the target number of multiple rule conditional statements to be output and / or the target number of multiple rule conditional statements to be output corresponding to the industry specification clauses in order from large to small according to the corresponding cumulative number, and superimposing them on the interface of the target design software for the user to view. In this way, by referring to the target number of multiple rule conditional statements to be output and / or the industry specification clauses corresponding to the multiple rule conditional statements to be output, the user can more conveniently trigger compliance operation events for the design scheme in the target design software to improve the compliance possibility of the operation event without further modifying the values of the operation attributes, thereby achieving the purpose of further improving the efficiency of generating qualified design schemes.
[0123] The target number can be determined based on the total cumulative number of times all rule conditional statements in the rule base have failed to be verified. For example, the target number can be positively correlated with the total cumulative number to avoid overlaying and displaying an excessive number of rule conditional statements to be output and / or an excessive number of industry specification clauses corresponding to the rule conditional statements to be output on the interface of the target design software. In this way, when a user triggers an operation event for a design solution in the target design software, they can more easily and quickly find the rule conditional statements to be output and / or the industry specification clauses corresponding to the rule conditional statements to be output that they want to reference.
[0124] In a second aspect, based on the method for processing industry standard texts in the above-mentioned embodiments, embodiments of the present application provide an apparatus for processing industry standard texts. The apparatus for processing industry standard texts is configured to execute the steps in any of the embodiments of the method for processing industry standard texts. Specifically, the apparatus for processing industry standard texts may include:
[0125] Acquisition module, used to obtain unstructured industry specification text;
[0126] An extraction module, which uses a neural network model to extract design objects, design attributes, and design constraints from industry specification texts;
[0127] A first generation module is used to generate corresponding rule condition statements based on design objects, design attributes and design constraints;
[0128] The second generation module is used to generate a rule base of industry standard text using rule conditional statements, and the rule base is used to constrain the design solution.
[0129] In a third aspect, embodiments of the present application provide a computer device that integrates any of the apparatuses for processing industry standard texts provided in the embodiments of the present application. The computer device includes a processor and a memory, wherein the memory stores a computer program configured to be executed by the processor to implement the method for processing industry standard texts described in any of the above embodiments, for example:
[0130] Obtain unstructured industry specification text; use a neural network model to extract design objects, design attributes, and design constraints from the industry specification text; generate corresponding rule conditional statements based on the design objects, design attributes, and design constraints; use the rule conditional statements to generate a rule base for the industry specification text, which is used to constrain the design plan.
[0131] In a fourth aspect, an embodiment of the present application provides a computer device that integrates any of the industry standard text processing devices provided in the embodiment of the present application. Figure 5 , which shows a schematic diagram of the structure of the computer device involved in the embodiment of the present application, specifically:
[0132] The computer device may include one or more processing core processors 501, one or more computer readable storage medium storage units 502, a power supply 503 and an input unit 504. Those skilled in the art will understand that Figure 5 The computer device structure shown in the figure does not constitute a limitation on the computer device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.
[0133] Processor 501 is the control center of the computer device. It connects the various components of the computer device using various interfaces and circuits. By running or executing software programs and / or modules stored in storage unit 502 and accessing data stored in storage unit 502, it performs various functions of the computer device and processes data, thereby providing overall monitoring of the computer device. Optionally, processor 501 may include one or more processing cores. Preferably, processor 501 may integrate an application processor and a modem processor, with the application processor primarily processing the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 501.
[0134] The storage unit 502 can be used to store software programs and modules. The processor 501 executes various functional applications and data processing by running the software programs and modules stored in the storage unit 502. The storage unit 502 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computer device, etc. In addition, the storage unit 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the storage unit 502 may also include a memory controller to provide the processor 501 with access to the storage unit 502.
[0135] The computer device also includes a power supply 503 for supplying power to various components. Preferably, the power supply 503 can be logically connected to the processor 501 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. The power supply 503 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.
[0136] The computer device may further include an input unit 504 , which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.
[0137] Although not shown, the computer device may further include a display unit, etc., which will not be described in detail here. Specifically, in the embodiment of the present application, the processor 501 in the computer device will load the executable files corresponding to the processes of one or more application programs into the storage unit 502 according to the following instructions, and the processor 501 will run the application programs stored in the storage unit 502 to implement various functions, such as:
[0138] Obtain unstructured industry specification text; use a neural network model to extract design objects, design attributes, and design constraints from the industry specification text; generate corresponding rule conditional statements based on the design objects, design attributes, and design constraints; use the rule conditional statements to generate a rule base for the industry specification text, which is used to constrain the design plan.
[0139] In a fifth aspect, embodiments of the present application provide a computer-readable storage medium, which may include: a read-only memory (ROM), a random access memory (RAM), a disk, or an optical disk. The computer-readable storage medium stores a computer program, which is configured to be executed by a processor to implement the method for processing industry standard texts as described in any of the above items, for example:
[0140] Obtain unstructured industry specification text; use a neural network model to extract design objects, design attributes, and design constraints from the industry specification text; generate corresponding rule conditional statements based on the design objects, design attributes, and design constraints; use the rule conditional statements to generate a rule base for the industry specification text, which is used to constrain the design plan.
[0141] In a sixth aspect, embodiments of the present application provide a computer program product or computer program, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to execute the method for processing industry specification texts as described in any one of the above items, for example:
[0142] Obtain unstructured industry specification text; use a neural network model to extract design objects, design attributes, and design constraints from the industry specification text; generate corresponding rule conditional statements based on the design objects, design attributes, and design constraints; use the rule conditional statements to generate a rule base for the industry specification text, which is used to constrain the design plan.
[0143] The above is a detailed introduction to the embodiments of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.
Claims
1. A method for processing industry standard texts, characterized in that: The processing method of the industry standard text includes: Obtain unstructured industry specification text; Using a neural network model, extracting design objects, design attributes, and design constraints from the industry specification text; Generate corresponding rule condition statements based on the design object, the design attributes and the design constraint conditions; The rule conditional statements are used to generate a rule base of industry standard texts, and the rule base is used to constrain the design solution.
2. The method for processing industry standard texts according to claim 1, characterized in that: The unstructured industry specification text includes multiple industry specification clauses. The use of the neural network model to extract design objects, design attributes, and design constraints from the industry specification text includes: Using a clause segmentation model, determining boundaries between adjacent industry specification clauses in the unstructured industry specification text; According to the boundary, determining a plurality of the industry specification clauses in the unstructured industry specification text; Named entity recognition is performed on each of the industry specification clauses to obtain the design object, the design attribute, and the design constraint condition in the industry specification clause.
3. The method for processing industry standard texts according to claim 2, characterized in that: The generating of corresponding rule condition statements based on the design object, the design attribute, and the design constraint condition includes: For the design object, the design attribute and the design constraint in each of the industry specification clauses, a rule condition statement of the industry specification clause is generated, and the rule condition statement records that the design attribute of the design object needs to meet the design constraint.
4. The method for processing industry standard texts according to claim 3, characterized in that: Before generating the rule conditional statements of the industry specification clause for the design object, the design attribute, and the design constraint condition in each industry specification clause, the method further includes: Performing fuzzy expression conversion processing on the design object, the design attribute, and the design constraint in each of the industry specification clauses to replace at least one fuzzy expression term in the design object, the design attribute, and the design constraint; A rule condition statement of the industry specification clause is generated by using at least one of the replaced design object, the design attribute, and the design constraint condition.
5. The method for processing industry standard texts according to claim 3, characterized in that: After generating the rule conditional statement of the industry specification clause, it also includes: Performing natural language classification on the industry specification clauses to determine a clause validity type of the industry specification clauses, where the clause validity type includes at least one of a mandatory clause, a recommended clause, and an explanatory clause; A rule condition statement that associates the clause effectiveness type with the industry specification clause.
6. The method for processing an industry standard text according to any one of claims 1 to 5, characterized in that: After generating a rule base of industry standard text using the rule conditional statements, the method further includes: Obtaining operation events for design solutions in target design software; Determine the operation object, operation attributes, and values of the operation attributes pointed to by the operation event; Using the rule conditional statements of the rule base, the operation object, and the operation attribute, a rule check is performed on the value of the operation attribute to obtain a check result; If the inspection result is failure, output inspection result prompt information of the value of the operation attribute.
7. The method for processing industry standard texts according to claim 6, characterized in that: After performing rule checking on the value of the operation attribute and obtaining the check result, the method further includes: If the test result is that the test fails, obtaining the target rule conditional statement that fails the test in the rule base; Determining a target clause validity type associated with the target rule conditional statement, where the target clause validity type includes at least one of a mandatory clause, a recommended clause, and an explanatory clause; Output prompt information of the effectiveness type of the target clause.
8. The method for processing industry standard texts according to claim 7, characterized in that: After obtaining the target rule conditional statement that fails the test in the rule base, the method further includes: Determining target design constraints in the target rule conditional statement; According to the target design constraint conditions, correction suggestion information of the value of the operation attribute is output.
9. A computer device, characterized in that: The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is configured to be executed by the processor to implement the method for processing the industry specification text according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is configured to be executed by a processor to implement the method for processing an industry specification text according to any one of claims 1 to 8.