Cinnamon Inc., which provides AI solutions to major domestic companies, has begun offering its proprietary RAG system “Super RAG” to The Norinchukin Bank, a national financial institution based on a cooperative organization of agriculture, forestry, and fisheries producers.
The Norinchukin Bank will promote business efficiency by using Cinnamon AI’s “Super RAG” to accurately import complex and massive amounts of data, including charts and tables, to improve data search capabilities and generate reliable answers using LLMs (large-scale language models). For the time being, the Bank will proceed with considering and implementing functions for the following business operations:
● Improving the efficiency of QA responses between departments in charge of operations and employees
● Improving operational efficiency and productivity in the investment and lending field
● Improve service and planning development capabilities by strengthening information sharing between head office and sales offices
Also Read: Microsoft Expands Its Copilot Studio with New AI Features
Cinnamon AI will continue to deepen its collaboration with The Norinchukin Bank, and will continue to automate processes through agent workflows that utilize the Super RAG API, as well as to test the introduction of AI agents. In addition, by promoting operational efficiency using generative AI technology, it will be possible to focus personnel on core operations, which will contribute to strengthening competitiveness and improving services.
“Super RAG” is highly accurate without tuning and can utilize complex documents including charts and graphs
Cinnamon AI‘s “Super RAG” is a unique AI product that can build LLM that analyzes complex documents such as tables and figures and generates highly accurate answers without the need for tuning. It uses unique document analysis technology to perform advanced analysis of unstructured data that is not suitable for data utilization, which is said to account for 80% of the data held by companies, and enables optimal structuring according to the content type, realizing business automation by generating LLM answers using the RAG system. In addition to highly accurate searches using a graph database that understands the relationships between content units within documents, it also provides APIs that enable connection to various systems and applications.
With these features, Super RAG can be implemented in a wide range of business operations. For example, LLM can easily import huge amounts of specialized documents such as financial statements, technical information, and company regulations, and quickly generate appropriate answers. It can also be used for operations that require specialized knowledge, such as responding to inquiries, creating business plans, writing reports, and predicting incidents, as well as for small-lot, high-mix operations that require tacit knowledge.
SOURCE: PRTimes
