<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>企业数据 on Text Matrix</title><link>https://txtmix.com/tags/%E4%BC%81%E4%B8%9A%E6%95%B0%E6%8D%AE/</link><description>Recent content in 企业数据 on Text Matrix</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Wed, 11 Nov 2026 08:18:21 +0800</lastBuildDate><atom:link href="https://txtmix.com/tags/%E4%BC%81%E4%B8%9A%E6%95%B0%E6%8D%AE/index.xml" rel="self" type="application/rss+xml"/><item><title>Auto Ontology：把「口径」从 prompt 里搬进数据库，让 Agent 先学会拒绝回答</title><link>https://txtmix.com/posts/tech/nvidia-auto-ontology-semantic-layer-guide/</link><pubDate>Tue, 10 Nov 2026 03:30:16 +0800</pubDate><guid>https://txtmix.com/posts/tech/nvidia-auto-ontology-semantic-layer-guide/</guid><description>&lt;h2 id="核心判断"&gt;核心判断&lt;/h2&gt;
&lt;p&gt;企业数据问答的瓶颈通常不在模型推理能力，而在「口径」。同一句“收入”，财务系统按确认时点算，运营系统按下单时点算，另一个报表工具里它干脆是另一列的别名。模型再强，面对三个互不兼容的口径也只能挑一个猜——而猜错的那个数字，答得越快越有害。&lt;/p&gt;</description></item></channel></rss>