康泰纳仕用Amazon Bedrock打造多模态视频发现方案

AI 摘要

康泰纳仕（Condé Nast）与AWS生成式AI创新中心合作，基于Amazon Bedrock和Amazon OpenSearch Service构建了多模态视频发现方案，采用TwelveLabs Marengo嵌入模型对视频转录、视觉和音频信号进行联合编码。该方案将编辑团队的内容发现时间从平均250分钟缩短至2分钟以内，覆盖Vogue、GQ、Vanity Fair、Wired等品牌，解决了原有搜索工具无法理解视频内容、依赖人工元数据和机构知识的问题。

正文节选

How Condé Nast built multimodal video discovery with Amazon Bedrock Condé Nast’s editorial teams had no fast way to do multimodal video discovery. They were spending an average of 250 minutes per content discovery task, manually scrubbing through a library of more than 140,000 videos. They relied on titles and descriptions to find relevant clips. In a media environment where speed-to-market directly determines revenue capture, this process created measurable operational drag across brands such a

发布时间：2026-09-29 23:55

抓取时间：2026-09-30 00:37

来源机构：AWS