English(EN) By shifting from standard search to "Modular RAG," Japan's Shionogi Pharmaceutical boosted its internal AI search accuracy from a coin-flip 50% to 90%. Working

盐野义制药公司通过模块化RAG将AI搜索准确率提高到90%

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-04 19:31

日本的盐野义制药公司通过实施“模块化RAG”系统，显著提高了其内部AI搜索能力。这一转变将准确率从50%提高到90%，使AI代理能够有效处理复杂的制药数据和Excel表格等非结构化信息。此次成功集成凸显了工程专业知识在部署企业AI解决方案中的日益重要性。 AI

影响展示了像模块化RAG这样的先进AI技术如何解决特定的企业数据挑战，提高运营效率。

排序理由这是AI技术在公司内部的具体应用，而非前沿发布或重大的行业性事件。

在 Mastodon — fosstodon.org 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

报道来源 [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-08-04 19:31

By shifting from standard search to "Modular RAG," Japan's Shionogi Pharmaceutical boosted its internal AI search accuracy from a coin-flip 50% to 90%. Working

By shifting from standard search to "Modular RAG," Japan's Shionogi Pharmaceutical boosted its internal AI search accuracy from a coin-flip 50% to 90%. Working with Classmethod, they built AI agents that autonomously navigate complex, highly regulated drug data and messy Excel sh…

链接 asiaai.fyi/issue-55

报道来源 [1]

By shifting from standard search to "Modular RAG," Japan's Shionogi Pharmaceutical boosted its internal AI search accuracy from a coin-flip 50% to 90%. Working

相关话题