This study introduces and experimentally validates a novel approach that combines Instruction fine-tuning and Low-Rank Adaptation (LoRA) fine-tuning to optimize the performance of Large Language Models (LLMs). These models have become revolutionary tools in natural language processing, showing remarkable performance across diverse application areas. However, optimizing their performance for specific domains necessitates fine-tuning of the base models (FMs), which is often limited by challenges such as data complexity and resource costs. The proposed approach aims to overcome these limitations by enhancing the performance of LLMs, particularly in the analysis precision and efficiency of national Research and Development (R&D) data. The study provides theoretical foundations and technical implementations of Instruction fine-tuning and LoRA fine-tuning. Through rigorous experimental validation, it is demonstrated that the proposed method significantly improves the precision and efficiency of data analysis, outperforming traditional fine-tuning methods. This enhancement is not only beneficial for national R&D data but also suggests potential applicability in various other data-centric domains, such as medical data analysis, financial forecasting, and educational assessments. The findings highlight the method's broad utility and significant contribution to advancing data analysis techniques in specialized knowledge domains, offering new possibilities for leveraging LLMs in complex and resource- intensive tasks. This research underscores the transformative potential of combining Instruction fine-tuning with LoRA fine-tuning to achieve superior performance in diverse applications, paving the way for more efficient and effective utilization of LLMs in both academic and industrial settings.

The electrification of transportation is expected to greatly contribute to achieving the global climate change target. This study analyzed technological competitiveness in the fuel cell electric vehicle (FCEV) field based on patent family and citation index. Technology analysis was conducted by dividing FECV into six sub-technology areas based on IPC with fuel cell system, fuel cell technology, vehicle system, hydrogen storage and fueling, catalyst technology and etc. The largest number of patents are being filed in the fuel cell system technology field, and the fields with high growth rates over the past 10 years (2012-2022) were vehicle systems (12.4%) and hydrogen storage fuel field(11.5%). As of 2021, among global automakers, Toyota ranks the first in patent applications for FECV followed by Hyundai Motors in Korea, followed by Honda and Audi, with an average annual growth rate of 19.8%, the highest among competitors.

As the uncertainty of technology development and market needs increases due to changes in the global business environment, the interest and demand for R&D activities of individual companies are increasing. To respond to these environmental changes, technology commercialization players are paying great attention to enhancing the qualitative competitiveness of R&D. In particular, R&D companies in the marine and fishery sector face many difficulties compared to other industries. For example, the R&D environment is barren, it is challenging to secure R&D human resources, and it is facing a somewhat more difficult environment compared to other sectors, such as the difficulty in maintaining R&D continuity due to the turnover rate of researchers. In this study, based on the empirical data and patent status of private companies closely related to the R&D technology status, big data analysis, and simulation analysis methods were used to identify the relative position of individual companies' R&D capabilities and industrial perspectives. In this study, based on industrial evidence and patent applications closely related to the R&D technology status, the R&D capabilities of individual companies were evaluated using extensive data analysis and simulation analysis methods, and a statistical test was performed to analyze if there were differences in capabilities from an industrial point of view. At this time, the industries to be analyzed were based on all sectors, the maritime industry, the fisheries industry, and the maritime industry integration sector. In conclusion, it was analyzed that there was a certain level of difference in the R&D capabilities of individual companies in each industry sector, Therefore when developing a future R&D capability system, it was confirmed that it was necessary to separate the population for each industry and establish a strategy.