share_log

三井化学、生成AIを活用した特許チャットを開発

Mitsui Chemicals has developed a patent chat using Generative AI.

Mitsui Chemicals ·  Dec 24, 2024 23:00

Mitsui Chemicals Co., Ltd. (Headquarters: Chuo-ku, Tokyo; President: Hashimoto Osamu) has developed a platform equipped with a uniquely developed generative AI chat to respond to highly specialized business needs specific to the chemical field, such as reading tables of experimental results and understanding chemical structural formulas in the chemical field. Demonstration tests will be completed through use by business divisions and research and development departments within 2024, and full-scale internal operation will begin in 2025.

This initiative promotes digital transformation (DX) in the business domain, and aims to create new product development ideas, product top line (sales), and expand market share. By combining the chemical expertise of our researchers and engineers with generative AI, we can lead to new value that could not be found using conventional methods.

The platform developed this time has 3 functions. First, it is equipped with a patent analysis function that responds to user questions from a huge amount of patent information, and can be used for patent searches, issue extraction, and technology trend research. Second, it incorporates a new application search function that derives information essential for new application search from large-scale patent information, and supports the discovery of new applications and the drafting of application candidates. Third, it implements a sales support function that derives knowledge about sales activities from internal information and web information, and can be used for market research, business partner discovery, competitive analysis, etc.

Big

Regarding the “patent analysis” function and the “new application search” function, an 80% reduction in work time was confirmed in experiments conducted with the cooperation of business divisions and research and development departments. In particular, in analyzing technical documents containing structural formulas and tabular data, significant efficiency improvements can be expected compared to conventional methods. Furthermore, the “business proposal” function can extract and analyze information not only from text data, but also from tabular data and structural formulas of compounds, and responds to complex information processing needs specific to the chemical field.

Big
Big

The knowledge gained through this initiative will contribute to the development of the chemical industry as a whole, and it is our policy to actively promote industry-academia collaboration and collaboration with other companies.

over

The translation is provided by third-party software.


The above content is for informational or educational purposes only and does not constitute any investment advice related to Futu. Although we strive to ensure the truthfulness, accuracy, and originality of all such content, we cannot guarantee it.
    Write a comment