MRI and PKUTECH jointly developed "AI Memory RAG," a new retrieval-augmented generation technology that enables analysis and answers informed by past discussions and decision-making processes—addressing a key limitation of traditional RAG, which struggles to track evolving information and historical context in continuously accumulated documents like news and meeting minutes.
The new technology structures documents across temporal, network, and change-history dimensions, allowing organizations to make faster and more informed decisions in fields such as news monitoring, intelligence analysis, development management, and knowledge transfer.
何が起きたか
シンクタンク・コンサルティングの三菱総合研究所(MRI)とAI・データ分析のPKUTECH(ピーケーユーテック)は、7月8日に新しいRAG(検索拡張生成)技術「AI Memory RAG」を共同開発したと発表しました。過去の議論や判断プロセスに照らした横断的な分析・回答ができるのが特徴です。
なぜ重要か
従来のRAGは類似した情報の検索が中心で、継続的に蓄積されるニュースや議事録に関して、過去の議論や変更の経緯を踏まえた回答が難しく、時間経過による変化も把握しにくいという課題がありました。新技術はこうした制限を克服し、実務での迅速で適切な意思決定が可能になるとみられます。
注目点
AI Memory RAGは、ニュースや議事録などの文書を時系列構造・グラフ(ネットワーク)構造・リポジトリ(変更履歴)構造の3つの形式で自動判定して保持します。ニュース監視・インテリジェンス分析、開発管理・議事録管理、ナレッジ継承などの分野での活用を想定しており、両社は実証を通して実用性を高め、ソリューション化を目指しています。
Ask the AI about this article →
The development of AI Memory RAG reflects a growing recognition of a practical gap in enterprise AI deployment. While traditional RAG has become a standard approach for grounding language models in proprietary data, it operates primarily as a semantic search tool—retrieving similar documents or passages without full understanding of how information has evolved or changed. Organizations increasingly face a different problem: they need AI systems that can trace back through accumulated institutional knowledge, understand how decisions were made in the past, and apply that historical context to new questions.
AI Memory is an emerging paradigm that addresses this by having AI systems maintain persistent memory of conversations and knowledge over time, mimicking human institutional memory. By combining this with structured data representations—temporal sequences for time-stamped information, graph structures for relationships between people and concepts, and change-history structures for tracking decisions and reversals—MRI and PKUTECH have created a system that can retrieve not just "what was said" but "how we got here." This is particularly valuable in domains like intelligence analysis and development management, where understanding the evolution of thinking and the rationale behind decisions is as important as the decisions themselves.
For example, today's edition would include:
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. Q&As are published on this page for other readers too.
BHP, the world's largest mining company by market capitalization, has deployed AI across its operations
Team Liquid announced a new five-year extension of its long-running collaboration with Dell Technologies' Alie…
A University of Mississippi study published in Journal of Interactive Advertising found that AI ads succeed wh…
Goldman Sachs Research says AI supply and demand won't balance until the first half of 2028
Lam Research broke ground yesterday on a new lab in Tualatin, Oregon
Visa, Mastercard, and Fiserv joined the Agentic Payments Alliance (APA), a 26-company coalition led by stablec…
