Intelligent AI document processing specialist company Jimmy Mission announced on the 22nd that it was selected for the 'Small and Medium Business Technology Innovation Development Project Market Expansion' research project hosted by the Ministry of SMEs and Startups.
The selected research project is 'Research and Development of VLM-based Multimodal Intelligent OCR Solution', and through this research, G-Mission plans to overcome the limitations of existing deep learning AI OCR technology and develop an intelligent document processing solution suitable for the AI transition (AX) era.
A Visual Language Model (VLM) is a multimodal model that simultaneously learns and analyzes visual information, such as images and layouts, in addition to text recognition. While conventional OCR focuses on character extraction, VLM-based multimodal OCR comprehensively analyzes text, tables, graphics, and formatting within a document, enabling a comprehensive understanding of the document's overall meaning and context.
Gmission currently utilizes AI OCR to provide automatic document format classification, automatic personal information masking, and LLM-based summarization and search technology. This research and development will integrate VLM technology into this technology to enhance the understanding and utilization of the entire document's meaning.
This allows users to experience an intelligent document processing environment that goes beyond simple text extraction and reflects the meaning and context of each item within a document. For example, even numeric data can be extracted based on format, such as account numbers or resident registration numbers, and only the desired items can be selectively summarized. Furthermore, context-based search capabilities enable users to quickly and accurately locate necessary information within vast documents, which is expected to enhance work efficiency.
Jimision CEO Han Jun-seop stated, “Through this research and development, we will secure advanced document processing technology and present innovative AI solutions that can be utilized in various industries such as the public, financial, medical, and corporate sectors.”
- See more related articles
You must be logged in to post a comment.