Earticle

본 연구는 기업의 AI Transformation(AX)을 지원하기 위해, Vision Language Model(VLM) 기반 지능 형 문서처리 플랫폼을 설계하고, Qwen2.5VL-7B를 활용한 영수증 처리 프로토타입을 구현하였다. 제안된 플랫폼 은 3-Tier 마이크로서비스 아키텍처를 기반으로, 프롬프트 관리 체계와 기능별 모듈화를 통해 유연하고 확장 가능 한 구조를 구현하였다. 실험 결과, 평균 91.7%의 정보 추출 정확도를 달성하였으며, 사전 템플릿 없이 다양한 문서 형식에 대응 가능한 처리 유연성을 바탕으로 실무 적용 가능성을 입증하였다. 본 연구는 OCR 중심 기술의 한계를 보완하는 프롬프트 기반 VLM 아키텍처를 실증적으로 제시하고, 금융·물류·의료 등 산업 전반에서 적용 가능한 문 서 자동화 기반을 제공하였다는 점에서 학문적·실무적 의의를 갖는다.

This study supports corporate AI Transformation (AX) by designing a document processing platform based on a Vision Language Model (VLM) and implementing a prototype using Qwen2.5VL-7B. The platform employs a three-tier microservice architecture with prompt management and modular components to ensure flexibility and scalability. Experiments showed an average information extraction accuracy of 91.7%, and the system demonstrated practical applicability by handling diverse document formats without predefined templates. This research provides an empirical implementation of a prompt-based VLM architecture that overcomes limitations of OCR technologies, offering academic and practical value as a foundation for document automation across sectors such as finance, logistics, and healthcare.

디지털화(Digitalization)가 우리의 비즈니스 환경에 다양한 변화와 혁신을 일으키고 있다. 제조업에서는 오래전 부터 자동화를 위해 로봇을 활용하여 처리속도 및 품질에 혁신을 이루었다. RPA는 이러한 제조현장의 혁신을 사무공간 으로 가져온 것이라고 할 수 있다. 본 연구의 목적은 사무공간에서 단순 반복적으로 이루어지는 업무에 대해 생산성을 향상시키는 것을 그 목적으로 한다. 이러한 생산성 향상과 관련하여, 비즈니스 자동화(Business Automation)에 대한 개념을 살펴본 후, 비즈니스 문서 작업과 관련하여 자동화의 가능성을 확인하기 위해 5가지 업무영역을 대상으로 애자 일 방법론을 활용하여 시뮬레이션을 수행하였다. 결론적으로, 품질점검 관련 97.3%, 편집 디자인 관련 31.7%의 생산성 향상이 가능함을 확인하였으며, 실제 업무에 적용하기 위한 방향성에 대해서도 살펴보았다. 향후 연구에서는 이러한 결과를 바탕으로 IPA(Intelligent Process Automation)의 적용방안에 대해 진행하고자 한다.

Digitalization is creating a variety of changes and innovations in our business environment. In manufacturing, robots have long been used for automation to innovate processing speed and quality. The RPA brings these innovations in manufacturing sites to the office space. The purpose of this study is to improve productivity for simple, repetitive tasks in these office space. For identify the potential of automation related to productivity improvement, I looked at the concept of business automation, and then simulated the five areas of business documentation works with agile methodology. In conclusion, I confirmed that productivity improvement of 97.3% in quality inspection and 31.7% in editorial design is possible, and examined the direction to apply to actual work. Based on these results, future study will explore the application of Intelligent Process Automation (IPA).

This paper suggests a specific model that could efficiently improve the interaction and the interface between MES(Manufacturing Execution System) server and POP(Point of Production) terminal through electronic document server and electronic pen, bluetooth receiver and form paper in disassembly and process inspection works. The proposed model shows that the new method by electronic document automation system can more efficiently perform to reduce processing time for maintenance work, compared with the current approach by handwritten processing system. It is noted in case of the method by electronic document automation system that the effects of proposed model are as follows; (a) While the processing time per equipment for maintenance by the current method was 300 minutes, the processing time by the new method was 50 minutes. (b) While the processing error ratio by the current method was 20%, the error ratio by the new method was 1%.

The nuclear design analysis requires time-consuming and erroneous model-input preparation, code run, output analysis and Quality assurance process. To reduce human effort and improve design Quality and productivity, Innovative Design Processor (IDP) is being developed. Two basic principles of IDP are the document-oriented design and the web-based design. The document-oriented design is that. if the designer writes a design document called active document and feeds it to a special program, the final document with complete analysis, table and plots is made automatically. The active documents can be written with Microsoft Word or created automatically on the web, which is another framework of IDP. Using the proper mix-up of server side and client side programming under the LAMP (Linux/Apache/MySQL/PHP) environment. the design process on the web is modeled as a design wizard stYle so that even a novice designer makes the design document easily. This automation using the IDP is now being implemented for all the reload design of Korea Standard Nuclear Power Plant (KSNP) type PWRs. The introduction of this process will allow large reduction in all reload design efforts of KSNP and provide a platform for design and R&D tasks of KNFC.

본 논문은 인보이스 문서 이미지에 문서 처리 자동화를 적용하기 위한 문서 구조 인식 방법과 문서 구조 인식 결과를 토대로 스프레드문서 형태로 출력하는 방법을 제안한다. 딥러닝 OCR 엔진을 통해 문서 내 단어 블록들과 해당 블록들의 문자 인식 결과를 얻는다. 단어 블록의 위치 정보들을 통해 같은 행과 같은 열에 존재하는 단어 블록들을 검출한다. 단어 블록들의 배치 정보를 통해 문서 영역을 분할한다. 문서의 구역 정보를 통해 얻어진 문서 구조를 토대로 스프레드시트의 알맞은 위치에 문자 인식 결과를 입력한다. 실험 결과 제안된 방법을 통한 항목 배치는 평균 92.30%의 정확도를 보인다.

In this paper, we propose the methods of invoice document structure recognition and of making a spreadsheet electronic document. The texts and block location information of word blocks are recognized by an optical character recognition engine through deep learning. The word blocks on the same row and same column are found through their coordinates. The document area is divided through arrangement information of the word blocks. The character recognition result is inputted in the spreadsheet based on the document structure. In simulation result, the item placement through the proposed method shows an average accuracy of 92.30%.

With the rapid growth of the World Wide Web and electronic information services, information is becoming available on-Line at an incredible rate. One result is the oft-decried information overload. No one has time to read everything, yet we often have to make critical decisions based on what we are able to assimilate. The technology of automatic text summarization is becoming indispensable for dealing with this problem. Text summarization is the process of distilling the most important information from a source to produce an abridged version for a particular user or task. Information retrieval(IR) is the task of searching a set of documents for some query-relevant documents. On the other hand, text summarization is considered to be the task of searching a document, a set of sentences, for some topic-relevant sentences. In this paper, we show that document information, that is more reliable and suitable for query, using document length normalization of which is gained through information retrieval . Experimental results of this system in newspaper articles show that document length normalization method superior to other methods use query itself.

WWW(World Wide Web)와 온라인 정보 서비스의 급속한 성장으로 인해, 보다 많은 정보가 온라인으로 이용 혹은 접근 가능해 졌다. 이런 정보홍수로 접근 가능한 정보들이 과잉되는 문제가 발생했다. 이러한 과잉 정보 현상으로 인하여 시간적 제약이 뒤따르며 이용 가능한 모든 정보를 근거로 중요한 의사 결정을 내려야 한다. 문서 요약 자동화(Text Summarize Automation)는 이 문제를 처리하는데 필수적이다. 본 논문에서는 정보 검색을 통해 획득한 문서들을 일차적으로 문서 길이 정규화를 이용하여 질의에 적합하고 신뢰도가 더욱 높은 문서 정보를 얻을 수 있음을 보인다.

In this paper, we propose the method of a table structure recognition in various table types for document processing automation. A table with items surrounded by ruled lines are analyzed by detecting horizontal and vertical lines for recognizing the table structure. In case of a table with items separated by spaces, the table structure are recognized by analyzing the arrangement of row items. After recognizing the table structure, the areas of the table items are input into OCR engine and the character recognition result output to a text file in a structured format such as CSV or JSON. In simulation results, the average accuracy of table item recognition is about 94%.

The nuclear design analysis requires time-consuming and erroneous model-input preparation. code run. output analysis and quality assurance process. To reduce human effort and improve design quality and productivity. Innovative Design Processor (IDP) is being developed. Two basic principles of IDP are the document-oriented desigll and the web-based design. The document-oriented design is that. if the designer writes a design document called active document and feeds it to a special program. the final document with complete analysis. table and plots is made automatically. The active documents can be written with Microsoft Word or created automatically on the web. which is another framework of IDP. Using the proper mix-up of server side and client side programming under the LAMP (Linux/Apache/MySQL/PHP) environment. it e design process on the web is modeled as a design wizard style so that even a novice designer makes the design document easily. This automation using the IDP is now being implemented for all the reload design of Korea Standard Nuclear Power Plant (KSNP) type PWRs. The introduction of this process will allow large reduction in all reload design efforts of KSNP and provide a platform for design and R&D tasks of KNFC.