---
id: 20261110-T0-05
title: "Kuken Industries用OpenAI API检索70年冷却塔图纸，找图从近1小时缩至4.5分钟"
title_en: "Kuken Industries Cuts Drawing Search from Nearly an Hour to 4.5 Minutes with OpenAI API"
url: https://ai.daily.yangsir.net/daily/20261110-T0-05
issue_date: 2026-11-10
publish_date: 2026-11-09T08:00:00.000Z
category: news
source_name: "OpenAI News"
source_url: https://openai.com/index/kuken
---

# Kuken Industries用OpenAI API检索70年冷却塔图纸，找图从近1小时缩至4.5分钟

Kuken Industries通过OpenAI API检索公司70年积累的冷却塔图纸。此前工程师为一次维修找对应图纸要花近1小时，现在缩短到4.5分钟。这是把大模型用于传统制造业历史资料检索的落地案例：非结构化图纸档案加上语义检索，直接压缩维修准备时间。对拥有大量历史工程文档的企业，这类改造的收益可以直接按工程师工时折算。

## English Version

**Kuken Industries Cuts Drawing Search from Nearly an Hour to 4.5 Minutes with OpenAI API**

Kuken Industries uses the OpenAI API to search seven decades of cooling tower drawings. Finding the right drawing for a repair now takes 4.5 minutes, down from nearly an hour. It is a concrete case of applying LLMs to legacy manufacturing archives: semantic search over unstructured drawing collections directly cuts repair preparation time. For companies sitting on large historical engineering document sets, the payoff translates straight into engineering hours saved.

---

**来源**：[OpenAI News](https://openai.com/index/kuken)

**详情页**：https://ai.daily.yangsir.net/daily/20261110-T0-05

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*