Elastic Enables Innovation in Next Generation Knowledge Management with LG CNS

Elasticsearch enhances LG CNS’s KeyLook AI with hybrid search, achieving a 95% increase in search relevance to dramatically improve the accessibility and usability of corporate knowledge

Elastic Enables Innovation in Next Generation Knowledge Management with LG CNS

Media Contact
Alexia Russell
PR-team@elastic.co

Elastic (NYSE: ESTC), the Search AI company, today announced its successful collaboration with LG CNS, a leading digital transformation company in Korea, to help transform the company’s global knowledge management services with enhanced search for generative AI (GenAI).

LG CNS's KeyLook AI search algorithm is a retrieval augmented generation (RAG) system developed at its in-house AI Center. The company has integrated Elasticsearch into its search algorithm, increasing its search relevance rate to 95% while reducing data retrieval time by over 50%.

LG CNS delivers comprehensive consulting, system development, and operational services to drive digital transformation in Korea and globally. Drawing upon a legacy of expertise earned from years of success in large-scale IT initiatives and a deep understanding of GenAI and other advanced technologies, LG CNS empowers businesses to innovate and optimize through transformative digital solutions.

To serve the global market with leading knowledge management services, LG CNS needed to improve the overall search function of its KeyLook AI search algorithm so that its applications could cover all search-related fields and languages.

In particular, LG CNS needed to improve its search relevancy to better understand user intent. This required shifting from a traditional keyword-based search to a more sophisticated context-based vector search approach. By adopting Elasticsearch, LG CNS addressed the limitations of its previous RAG, improving search accuracy and leading to a 95% relevance rate.

"With vector search capabilities, Elasticsearch allows for contextually accurate, multi-lingual searches, enhancing the accessibility and usability of corporate knowledge more effectively and efficiently," said Vice President Yohan Chin, head of the AI Center at LG CNS.

The collaboration between Elastic and LG CNS also substantially improved the speed of data retrieval. By optimizing memory management and leveraging Elasticsearch’s scalable architecture, LG CNS successfully halved the time required to search extensive datasets.

Adopting Elasticsearch has also benefited LG CNS employees. The KeyLook AI algorithm leverages GenAI models to encode corporate data and index it within Elasticsearch. When a user enters a question on a search site, KeyLook AI identifies related documents and delivers them to a large language model (LLM). The LLM then delivers answers to users by compiling user-friendly, easy-to-understand answers. LG CNS can preserve the data governance of its proprietary corporate information and leverage the RAG applications using the power of Elastic Search AI.

“Gen-AI powered conversational queries are a powerful tool for next-generation knowledge management, helping to deliver the productivity, efficiency and user experience customers expect,” said Matthew Day, general manager & vice president, APJ & EMEA at Elastic. “As our collaboration continues with LG CNS, we will continue to explore new avenues of innovation available through LG CNS’s KeyLook AI and the Elastic Search AI Platform to benefit our shared customers.”

To find out more, read the customer story here.

About Elastic

Elastic (NYSE: ESTC), the Search AI Company, enables everyone to find the answers they need in real-time using all their data, at scale. Elastic’s solutions for search, observability and security are built on the Elastic Search AI Platform, the development platform used by thousands of companies, including more than 50% of the Fortune 500. Learn more at elastic.co.

Elastic and associated marks are trademarks or registered trademarks of Elastic N.V. and its subsidiaries. All other company and product names may be trademarks of their respective owners.