返回全部动态

uniopen 基于 Amazon Nova 定制零售审核模型并部署生产

原标题:How uniopen customized Amazon Nova to their retail moderation policies for production deployment

AWS Machine Learning Blog一手来源商业质量 71

AI 摘要

台湾统一企业集团旗下的数字通信与会员平台 uniopen 为其中文电商与会员渠道定制了内容审核模型。团队基于 Amazon Nova 2 Lite,通过 Amazon SageMaker AI 进行监督微调,并加入提示词级输出优化,以适配其按「行为(9 类)」和「主体(品牌/其他/禁止)」两轴划分的业务专属审核政策。方案将纠错数据、训练、评估与部署纳入统一工作流,并设置硬性/软性门禁与人工复核,在 737 个对话窗口的测试集上评估基线、微调及提示优化后的模型表现。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

How uniopen customized Amazon Nova to their retail moderation policies for production deployment uniopen is a digital communication and membership platform launched by Taiwan’s Uni-President Enterprises Group, connecting customers to ecommerce, membership benefits, and other retail experiences across web, tablet, and mobile channels. Across those channels, uniopen applies a moderation policy that classifies each interaction along two axes. The first is what behavior occurred (nine categories), a


发布时间:2026-10-01 23:33
抓取时间:2026-10-02 00:17
来源机构:AWS
阅读原文aws.amazon.com