Dynamic generation and intelligent HWP booklet automatic generation system for submission of railway precision diagnosis government offices through MCP and LLM linkage, and its control method

Abstract

The present invention relates to a system for dynamic generation of railway precision diagnostic data for submission to government agencies and an intelligent HWP booklet automatic generation system through the integration of MCP and LLM, and a control method thereof. To this end, the present invention relates to a system for dynamic generation and intelligent automatic HWP booklet generation for submission to government agencies regarding railway precision diagnostics through the integration of MCP and LLM, comprising: a standard template repository and input data that load and manage the client's standard task order form, field information, and formatting rule data; an MCP-based preprocessing binder connected to the standard template repository and input data that restructures data and relays communication to map unstructured knowledge data in JSON form, which is primarily output from the AI ​​engines of LLM and VLM, to HWP field IDs; and an HWP automatic typesetting module connected to the MCP-based preprocessing binder that injects parsed mapping data. The present invention provides a dynamic generation and intelligent HWP booklet automatic generation system for submission to government agencies for railway precision diagnosis through MCP and LLM integration, characterized by including: an AI text fitting model and a motion layout control model that are connected to an HWP automatic typesetting module, calculate the absolute pixel length of a target object to first adjust letter spacing and font size according to a shrink rate when a specified boundary overflow occurs, and execute a page break, create a new page, duplicate the header layout, and resume residual injection when insufficient remaining space is detected while traversing cell data within a table; and a booklet compiler that is connected to the AI ​​text fitting model and the motion layout control model, merges (appends) multiple HWP files that have completed individual generation, scans metadata style attributes, and renders an entire table of contents with hyperlinks at the top of the document. The present invention, configured as described above, provides an optimized system for dynamic generation and intelligent booklet production of HWP (Hangul Word Processor) administrative documents in government agency (Korea Railroad Corporation) standard through the integration of Model Context Protocol (MCP) and Large Language Model (LLM).

Description

Technology Field

[0001] An embodiment of the present invention relates to a system for dynamic generation and intelligent HWP booklet generation for submission to government offices for railway precision diagnosis through the integration of MCP and LLM, and more specifically, to provide a system for dynamic generation and intelligent booklet generation of administrative documents in HWP (Hangul Word Processor) format according to government office (railway administration) standards through the integration of Model Context Protocol (MCP) and Large Language Model (LLM). Background Technology

[0003] Unless otherwise indicated in this specification, the contents described in this identification item are not prior art for the claims of this application, and are not recognized as prior art simply because they are described in this identification item.

[0004] As is well known, the precision diagnosis and performance evaluation of railway facilities must go beyond a simple suitability or non-suitability judgment and conduct a comprehensive evaluation based on multifaceted indicators such as safety, durability, and usability.

[0005] In particular, the final deliverables of the railway precision diagnosis and performance evaluation must be submitted in strict compliance with the special HWP (Hangul) report format provided by the Korea National Railway Corporation and other organizations.

[0006] The realistic limitations of the writing process are as follows.

[0007] First, even though the latest AI (LLM) generates excellent analytical opinions and databases provide perfect numerical statistics, a bottleneck occurred where workers ultimately had to manually paste and edit content to place them within HWP formatting (e.g., table size, character width, letter spacing, captions, etc.) without visual distortion.

[0008] Second, particularly when variable-length data such as status photo sheets or comprehensive opinion reports in the form of long texts exceeded a single page, the cell format became distorted, requiring manual adjustments for page divisions (e.g., page breaks).

[0009] Third, the existing OLE / ActiveX method for automatically controlling HWP had poor stability in server-side and cloud integration environments, and it was difficult to process background merging of large volumes of documents.

[0011] In order to solve the aforementioned problems, the following prior art documents were developed in the past; however, a major problem still arose in that the problems of the aforementioned prior art could not be solved all at once. Prior art literature

[0013] Korean Registered Patent Publication No. 2841019 (July 28, 2025) has been registered. Korean Registered Patent Publication No. 2870142 (October 2, 2025) has been registered. Korean Registered Patent Publication No. 2870144 (October 2, 2025) has been registered. Korean Registered Patent Publication No. 2870125 (October 2, 2025) has been registered. Korean Registered Patent Publication No. 2870134 (October 2, 2025) has been registered. The problem to be solved

[0014] The present invention has been devised to resolve the various problems of the prior art described above. Its first objective is to equip a dynamic generation and intelligent HWP booklet automatic generation system with a standard template repository and input data, an MCP-based preprocessing binder, an HWP automatic typesetting module, an AI text fitting model, a motion layout control model, and a booklet compiler. The second objective of the present invention, based on the technical configuration described above, is to provide an optimized dynamic generation and intelligent booklet system for HWP (Hangul Word Processor) administrative documents conforming to government agency (Korea Railroad Administration) standards through the integration of the Model Context Protocol (MCP) and a Large Language Model (LLM). The third objective is to utilize the Model Context Protocol (MCP) to map unstructured analysis data and results generated by an external Large Language Model (LLM) or database into designated fields within an HWP (Hangul) document form (template), which is a strict government agency standard format, without error, and to provide an AI text that controls font size and character spacing according to variations in the volume of text content. The fourth objective is to provide a system that compiles a completed booklet with a single click by performing text fitting and dynamic pagination based on the length of table data, and to provide an engine that controls report generation in a cloud environment by establishing an HWP MCP (Model Context Protocol) communication interface that ensures secure and standardized bidirectional data communication between an LLM-based analysis agent and an HWP document view / editing engine, and the fifth objective is an AI text fitting algorithm that reduces and adjusts the text size when input data (e.g., AI natural language findings, dozens of field photos, etc.) exceeds the limited area of ​​an HWP table, andThe sixth objective is to apply Intelligent Pagination that automatically generates the next page, copies table headers, and recursively outputs remaining data; the sixth objective is to provide a one-click Booklet Compiler that merges multiple independently rendered unit report (hwp) files based on a script to simultaneously process, in the background, the automatic updating of sequential page numbers and reader lines for the entire document, as well as the generation of a Table of Contents (TOC) through title style extraction; the seventh objective is to enable direct drop-in of intellectual insights derived from LLM onto the conservative HWP formats of government offices without human 'copy and paste,' thereby instantly concluding the final delivery process; the eighth objective is to introduce layout technology where table formats flexibly respond to changes in document content and automatically expand, thereby fundamentally preventing output errors (e.g., text truncation); and the ninth objective is for the server engine to process everything from the composition of the table of contents to the integration of page numbers for the entire booklet (hundreds of pages) in the background. The administrative burden on engineers has been drastically reduced, and the 10th objective is to significantly improve the quality and reliability of the intelligent HWP booklet automatic generation system and the dynamic generation of railway precision diagnostic documents for submission to government agencies through the integration of MCP and LLM. means of solving the problem

[0016] To achieve this objective, the present invention relates to a system for dynamic generation and intelligent automatic HWP booklet generation for submission to government agencies regarding railway precision diagnostics through the integration of MCP and LLM, comprising: a standard template repository and input data that load and manage the client's standard task order form, field information, and formatting rule data; an MCP-based preprocessing binder connected to the standard template repository and input data that restructures data and relays communication to map unstructured knowledge data in JSON form, which is primarily output from the AI ​​engines of LLM and VLM, to HWP field IDs; and an HWP automatic typesetting module connected to the MCP-based preprocessing binder that injects parsed mapping data. The present invention provides a dynamic generation and intelligent HWP booklet automatic generation system for submission to government agencies for railway precision diagnosis through MCP and LLM integration, characterized by including: an AI text fitting model and a motion layout control model that are connected to an HWP automatic typesetting module, calculate the absolute pixel length of a target object to first adjust letter spacing and font size according to a shrink rate when a specified boundary overflow occurs, and execute a page break, create a new page, duplicate the header layout, and resume residual injection when insufficient remaining space is detected while traversing cell data within a table; and a booklet compiler that is connected to the AI ​​text fitting model and the motion layout control model, merges (appends) multiple HWP files that have completed individual generation, scans metadata style attributes, and renders an entire table of contents with hyperlinks at the top of the document.

[0017] In addition, the present invention relates to a control method using a system for dynamic generation and intelligent HWP booklet generation for submission to government offices for railway precision diagnosis through MCP and LLM integration, characterized by including: (a) a step of receiving unstructured analysis data and parsing fields using a data transfer module applying Model Context Protocol (MCP); (b) a step of operating an AI text fitting engine and detecting whether the target cell unit is exceeded; (c) a step of determining whether the single cell text input area is exceeded; (d) a step of operating a dynamic pagination engine and selecting dynamic insertion limits; (e) a step of determining whether the space of a multi-row / photo list table is exceeded; (f) a step of operating a document integration compiler and sequentially merging multiple HWP files after typesetting is complete; and (g) a step of completing a final single HWP booklet and matching and reflecting the Table of Contents (TOC) and page numbers. Effects of the invention

[0019] As described in detail above, the present invention provides an optimized system for dynamic generation and intelligent booklet production of government agency (Korea Railroad Administration) standard HWP (Hangul Word Processor) administrative documents through the integration of the Model Context Protocol (MCP) and a Large Language Model (LLM).

[0020] In addition, the present invention provides a system that maps unstructured analysis data and results generated by an external large language model (LLM) or database to a designated field within an HWP (Hangul) document form (template), which is a strict government standard format, without error by utilizing the Model Context Protocol (MCP), and controls the character size and spacing according to changes in the volume of text content using an AI text fitting function, and compiles a completed booklet with one click by performing dynamic pagination according to the length of table data.

[0021] The present invention provides an engine that controls report generation in a cloud environment by establishing an HWP MCP (Model Context Protocol) communication interface that ensures secure and standardized bidirectional data communication between an LLM-based analysis agent and an HWP document view / editing engine.

[0022] In addition, the present invention applies an AI Text Fitting algorithm that reduces and adjusts the text size when input data (e.g., AI natural language findings, dozens of field photos, etc.) exceeds the limited area of ​​an HWP table, and Intelligent Pagination that automatically generates the next page, copies the table header, and recursively outputs the remaining data.

[0023] Furthermore, the present invention provides a one-click booklet compiler that merges multiple independently rendered unit report (hwp) files based on a script to simultaneously process, in the background, the automatic updating of serial page numbers and reader lines of the entire document and the generation of a Table of Contents (TOC) through title style extraction.

[0024] In particular, this invention enables the direct drop-in of intellectual insights derived from LLM onto conservative HWP forms used by government offices without human 'copy and paste,' thereby instantly concluding the final delivery process.

[0025] In addition, the present invention introduces a layout technology in which the table format flexibly responds to changes in document content and automatically expands, thereby enabling the fundamental prevention of output errors (e.g., text truncation).

[0026] In addition, the present invention enables the server engine to process the table of contents for the entire booklet (on the scale of hundreds of pages) and the integration of page numbers in the background, thereby 혁신적으로 reducing the administrative effort of engineers.

[0027] Due to the aforementioned effects, the present invention enables a significant improvement in the quality and reliability of the intelligent HWP booklet automatic generation system and dynamic generation for submission to government agencies for railway precision diagnostics through the integration of MCP and LLM.

[0029] Hereinafter, a preferred embodiment of the present invention for achieving these effects will be described in detail with reference to the attached drawings. Brief explanation of the drawing

[0031] FIG. 1 is a block diagram of a system for dynamic generation for submission to government offices and intelligent HWP booklet automatic generation through MCP and LLM linkage applied in the present invention. FIG. 2 is a flowchart of the control method for the intelligent HWP booklet automatic generation system and dynamic generation for submission to government offices for railway precision diagnosis through MCP and LLM linkage applied in the present invention. Specific details for implementing the invention

[0032] The dynamic generation system for submitting to government offices for precise railway diagnosis and intelligent HWP booklet automatic generation system and control method applied in the present invention through MCP and LLM linkage are configured as shown in FIGS. 1 and 2.

[0033] In the following description of the present invention, if it is determined that a detailed description of related known functions or configurations may unnecessarily obscure the essence of the present invention, such detailed description will be omitted.

[0034] Furthermore, the terms described below are established considering their functions in the present invention, and since these may vary depending on the producer's intent or practice, their definitions should be based on the content throughout this specification.

[0035] In addition, the size and thickness of each component shown in the drawings are depicted arbitrarily for convenience of explanation, so the present invention is not necessarily limited to what is shown in the drawings.

[0036] First, the present invention relates to a dynamic generation and intelligent HWP booklet automatic generation system (100) for submission to government offices for railway precision diagnosis through MCP and LLM linkage, and is configured as follows.

[0037] That is, the present invention is equipped with a standard template repository and input data (110) that load and manage standard task instruction forms, field information, and format rule data.

[0038] In addition, the present invention is connected to the standard template repository and input data (110), and is equipped with an MCP-based preprocessing binder (120) that restructures data and relays communication to map unstructured knowledge data in JSON form, which is primarily output from the AI ​​engine of LLM and VLM, to an HWP template ID.

[0039] At this time, the MCP-based preprocessing binder (120) is preferably composed of a Model Context Protocol (MCP) applied data transfer module prepared to exchange an unstructured data payload generated from an external analysis unit including a large language model (LLM) with an HWP control module in a standardized form.

[0040] The present invention is also equipped with an HWP automatic typesetting module (130) that is connected to the MCP-based preprocessing binder (120) and injects parsed mapping data.

[0041] In addition, the present invention is connected to the HWP automatic typesetting module (130) and includes an AI text fitting model and an operation layout control model (140) that calculate the absolute pixel length of a target object, first adjust the letter spacing and font size according to the shrink rate when a specified boundary overflow occurs, and execute a page break, create a new page, duplicate the header layout, and resume residual injection when a lack of remaining space is detected while traversing cell data within a table.

[0042] The present invention is connected to the AI ​​text fitting model and operation layout control model (140), and is equipped with a booklet compiler (150) that merges (appends) a plurality of individually generated HWP files, scans metadata style attributes, and renders an entire table of contents with hyperlinks at the top of the document.

[0043] Meanwhile, the AI ​​text fitting model applied in the present invention is preferably configured as an AI text fitting engine that performs iterative rendering to insert input data into a document, and if the target exceeds a limited space, dynamically reduces the character ratio and font size of the input paragraph using a variable value calculated based on the excess ratio.

[0044] In addition, the operation layout control model (140) applied to the present invention is preferably configured as a dynamic pagination engine that, when the input data is a variable table or photo list of multiple rows, selects the remaining row insertion limit of the currently applied page and, when exceeded, automatically opens a new page and transfers the split top table header attributes as they are to provide continuity of writing.

[0045] On the other hand, the booklet compiler (150) applied to the present invention is preferably configured as a document integrator that merges multiple unit document files into a single HWP format file and automatically generates a table of contents (TOC) and page numbers based on specified rules through background operations.

[0046] Finally, it is desirable that the dynamic pagination engine applied in the present invention, when it detects at runtime that there is insufficient remaining row insertion space in the currently applied page during the process of circulating data insertion into a table, controls the process to maintain a consistent format across multiple documents by opening a new page via a background command, extracting the header cell range and attributes of the top table prior to splitting, automatically duplicating them to the top of the table within the new page, and then resuming the injection of the remaining data.

[0048] Meanwhile, the present invention can be modified in various ways and can take various forms when applying the above-mentioned components.

[0049] And it should be understood that the present invention is not limited to the specific form mentioned in the above detailed description, but rather should be understood to include all variations, equivalents, and substitutions within the spirit and scope of the invention as defined by the appended claims.

[0051] The effects of the system for dynamic generation of railway precision diagnostic data for submission to government agencies and the intelligent HWP booklet automatic generation system and control method, configured as described above through the MCP and LLM linkage of the present invention, are explained as follows.

[0052] First, the present invention provides a system for dynamically generating and intelligently bookleting administrative documents in the HWP (Hangul Word Processor) format, which is an optimized standard for government offices (Korea Railroad Corporation), through the integration of the Model Context Protocol (MCP) and a large language model (LLM). The third objective is to provide a system that utilizes the Model Context Protocol (MCP) to map unstructured analysis data and results generated by an external large language model (LLM) or database into designated fields within a HWP (Hangul) document template, which is a strict standard format for government offices, without error, and to provide an AI text fitting function that controls the font size and spacing according to changes in the volume of text content, and a system that compiles a completed booklet with one click by performing dynamic pagination according to the length of table data.

[0053] To this end, Figure 1 applied to the present invention is a block diagram of a system for dynamic generation for submission to government offices for railway precision diagnosis and intelligent HWP booklet automatic generation through MCP and LLM linkage, showing an MCP communication-based LLM → HWP data automatic binding process.

[0054] In addition, Figure 2 is a flowchart of the control method for the railway precision diagnosis system for submission to government offices and the intelligent HWP booklet automatic generation system through the linkage of MCP and LLM applied in the present invention, showing the flowchart of the automatic generation of government administrative documents and dynamic booklet method.

[0055] The effects of the present invention will be explained in more detail below.

[0056] The present invention relates to a control method using an intelligent HWP booklet automatic generation system (100) for dynamic generation for submission to government offices of railway precision diagnostics through MCP and LLM linkage, and performs each of the following steps.

[0057] (a) The Model Context Protocol (MCP) applied data transfer module undergoes the step (S100) of receiving unstructured analysis data and parsing fields.

[0058] At this time, the above step (S100) involves receiving an unstructured analysis result data payload generated from an external engine of a large language model (LLM) through a data transfer module applying the Model Context Protocol (MCP) and parsing it into an HWP field structure.

[0059] (b) The AI ​​text fitting engine operation and the detection step (S200) of whether the target cell unit is exceeded are performed.

[0060] At this time, in the above step (S200), when the AI ​​text fitting engine transmits the parsed data to the template document press frame for rendering, it calculates the ratio of excess within the target unit cell and variably reduces the paragraph width and font size within a preset allowable range.

[0061] (c) A step for determining whether to detect exceeding a single cell text input area (S300) is performed.

[0062] (d) undergoes a dynamic pagination engine operation and dynamic insertion limit selection step (S400).

[0063] At this time, the above (S400) allows the dynamic pagination engine to select insertion limits and perform automatic page splitting and duplication of the header attributes of the top table prior to splitting.

[0064] (e) Perform a step (S500) to determine if the table space for multiple rows / photos exceeds the limit.

[0065] (f) The document integration compiler operation and typesetting completion are followed by a step of sequentially merging multiple HWP files (S600).

[0066] At this time, in the above step (S600), the document integration compiler sequentially merges multiple HWP unit documents that have completed typesetting and updates the title style and header / footer specifications.

[0067] (g) The final single HWP booklet is completed, and the Table of Contents (TOC) and page number matching and reflection step (S700) is performed.

[0068] At this time, the above step (S700) integrates and completes a single HWP booklet file in which the entire table of contents (TOC) and page numbers are matched.

[0069] Meanwhile, in the above (c) step of determining whether to detect exceeding the single cell text input area (S300), if Yes, the present invention proceeds to variable reduction of paragraph width and character size (within the allowable range) of (S301), and if No, proceeds to (S400).

[0070] Furthermore, in the above (e) step of determining the excess space of a multi-row / photo list table (S500), if Yes, the present invention proceeds to rendering the remaining data with the automatic page break header attribute duplication in (S501), and if No, proceeds to (S600).

[0072] The present invention, as described above, provides a system for the dynamic generation and intelligent booklet creation of optimized HWP (Hangul Word Processor) administrative documents in government agency (Korea Railroad Administration) standard formats through the integration of the Model Context Protocol (MCP) and a Large Language Model (LLM). The third objective is to provide a system that utilizes the Model Context Protocol (MCP) to map unstructured analysis data and results generated by external Large Language Models (LLM) or databases into designated fields within HWP (Hangul) document templates—which are strict government agency standard formats—without error, and to provide an AI Text Fitting function that controls font size and character spacing according to variations in text content volume, as well as a system that compiles a completed booklet with a single click by performing Dynamic Pagination based on the length of table data. In particular, it enables the intellectual insights derived from the LLM to be applied to the conservative HWP formats of government agencies without human 'copy and paste'. It enables direct drop-in, allowing the final delivery process to be completed instantly; it introduces layout technology that flexibly adapts table formats to changes in document content and automatically expands, thereby fundamentally preventing output errors (e.g., text truncation); and it provides the effect of 혁신적으로 reducing the administrative burden on engineers by having the server engine process tasks such as configuring the table of contents and integrating page numbers for full booklets (hundreds of pages) in the background. Industrial applicability

[0074] The technical concept of the present invention, which enables the dynamic generation of railway precision diagnostic data for submission to government agencies and the automatic generation of intelligent HWP booklets through the linkage of MCP and LLM, and the control method thereof, is capable of repeatedly producing identical results in practice. In particular, since implementing such an invention promotes technological advancement and contributes to industrial development, it is fully worthy of protection. Explanation of the symbols

[0075] <Explanation of symbols for major parts of the drawing> 100: Dynamic Generation and Intelligent HWP Booklet Automatic Generation System 110: Standard Template Repository and Input Data 120; MCP-based preprocessing binder 130: HWP Automatic Typesetting Module 140: AI Text Fitting Model and Behavior Layout Control Model 150; Booklet compiler

Claims

Claim 1 The invention relates to a system (100) for dynamic generation and intelligent HWP booklet automatic generation for submission to government offices regarding railway precision diagnosis through MCP and LLM integration, comprising: a standard template repository and input data (110) that loads and manages the ordering party's standard task instruction form, field information, and formatting rule data; an MCP-based preprocessing binder (120) connected to the standard template repository and input data (110) that restructures data and relays communication to map unstructured knowledge data in JSON form, which is primarily output from the AI ​​engines of LLM and VLM, to an HWP field ID; an HWP automatic typesetting module (130) connected to the MCP-based preprocessing binder (120) that injects parsed mapping data; and a system connected to the HWP automatic typesetting module (130) that calculates the absolute pixel length of a target object, primarily adjusts the letter spacing and font size according to the shrink rate when a specified boundary overflow occurs, and cell data within a table A dynamic generation and intelligent HWP booklet automatic generation system for submission to government offices for railway precision diagnosis through MCP and LLM integration, characterized by including: an AI text fitting model and a motion layout control model (140) that executes a page break, creates a new page, and resumes residual injection after duplicating the header layout when a shortage of remaining space is detected during traversal; and a booklet compiler (150) connected to the AI ​​text fitting model and motion layout control model (140), which appends multiple HWP files that have been individually generated, scans metadata style attributes, and renders a full table of contents with hyperlinks at the top of the document. Claim 2 A system for dynamic generation and intelligent HWP booklet automatic generation for submission to government offices for railway precision diagnosis through MCP and LLM integration, characterized in that, in claim 1, the AI ​​text fitting model is composed of an AI text fitting engine that performs iterative rendering to insert input data into a document and, if the target exceeds a limited space, first dynamically reduces the ratio and font size of the input paragraph using a variable value calculated for the excess amount. Claim 3 A system for dynamic generation and intelligent HWP booklet automatic generation for submission to government offices for railway precision diagnosis through MCP and LLM integration, characterized in that, in claim 1, the operation layout control model (140) is configured as a dynamic pagination engine that, when the input data is a variable table of multiple rows or a photo list, selects the remaining row insertion limit of the currently applied page and, when exceeded, automatically opens a new page and transfers the split top table header attributes as they are to provide continuity of creation. Claim 4 A system for dynamic generation and intelligent HWP booklet generation for submission to government offices for railway precision diagnosis through MCP and LLM integration according to claim 1, wherein the booklet compiler (150) is composed of a document integrator that merges multiple integrated unit document files into a single HWP format file and automatically generates a table of contents (TOC) and page numbers based on specified rules through background operations. Claim 5 A system for dynamic generation and intelligent HWP booklet automatic generation for submission to government offices for railway precision diagnosis through MCP and LLM integration according to claim 3, characterized in that, when the dynamic pagination engine detects at runtime that there is insufficient remaining row insertion space in the currently applied page during the process of circulating and inserting data into a table, it opens a new page through a background command, extracts the header cell range and attributes of the top table prior to splitting, automatically duplicates them at the top of the table within the new page, and then resumes the injection of remaining data to maintain a consistent format across multiple documents. Claim 6 The method of control using a system (100) for dynamic generation and intelligent HWP booklet automatic generation for submission to government offices for railway precision diagnosis through the linkage of MCP and LLM of claim 1 comprises: (a) a step of receiving unstructured analysis data and parsing a field using a data transfer module applying a Model Context Protocol (MCP) (S100); (b) a step of operating an AI text fitting engine and detecting whether the target cell unit is exceeded (S200); (c) a step of determining whether the single cell text input area is exceeded (S300); (d) a step of operating a dynamic pagination engine and selecting dynamic insertion limit points (S400); (e) a step of determining whether the space of a multi-row / photo list table is exceeded (S500); (f) a step of operating a document integration compiler and sequentially merging multiple HWP files after typesetting is complete (S600); (g) a step of final single HWP booklet completion and matching and reflection of the Table of Contents (TOC) and page numbers (S700); wherein, in the above (c) step of determining whether to detect exceeding the single cell text input area (S300), if Yes, proceed to variable reduction of paragraph width and character size (within the allowable range) of (S301), and if No, proceed to (S400); and in the above (e) step of determining exceeding the space of the multi-row / photo list table (S500), if Yes, proceed to rendering of residual data with duplicated header attributes of automatic page break of (S501), and if No, proceed to (S600). This characterizes a control method for a system for dynamic generation and intelligent HWP booklet generation for submission to government offices for railway precision diagnosis through MCP and LLM integration. Claim 7 delete Claim 8 delete

Images