---
格式版本: 2
标题: "Amazon SageMaker Unified Studio now supports data profiling and anomaly detection"
原文链接: "https://aws.amazon.com/cn/about-aws/whats-new/2026/05/smus-data-profiling/"
发布日期: "2026-08-18"
发布时间校准状态: "found"
发布时间需复核: "否"
发布时间来源: "llm:local:original_script_field"
发布时间证据: "postDateTime: 2026-08-18T18:49:00Z"
发布时间校准原因: "该候选来自原始脚本字段postDateTime，明确表示文章发布时间，且无其他更优候选。"
发布时间校准置信度: "1"
发布时间候选数量: 1
发布时间严格候选数量: 0
发布时间原页读取状态: "source template page reused from URL open"
发布时间未找到原因: ""
发布时间校准时间: "2026-08-21T09:56:07+08:00"
发布时间仲裁状态: "confirmed"
发布时间仲裁尝试次数: 1
发布时间仲裁耗时毫秒: 16816
发现时间: "2026-08-21T09:50:45+08:00"
入库时间: "2026-08-21T01:56:26.544Z"
来源平台: "固定入口"
搜索渠道: "fixed_url"
搜索词: "https://aws.amazon.com/new"
匹配关键词:
  []
相关厂家:
  - "AWS"
相关专家:
  []
内容类型: "网页"
抓取工具: "Free Fetch + Defuddle"
清洗工具: "Defuddle Markdown + Defuddle/Readability 正文提取"
原始附件:
  []
AI优质: "否"
AI打分: 13
AI分档: "非优质"
AI质检状态: "不通过"
AI打分理由: "内容为AWS SageMaker数据画像与异常检测功能，属数据质量管理工具，与超节点、AI Rack、机柜级AI基础设施、供电散热互连及量产落地均无关联。"
AI质检模型: "ali-deepseek-v4-flash"
AI质检时间: "2026-08-21T09:57:27+08:00"
AI主题相关性: 0
AI来源权威性: 5
AI新颖性: 0
AI技术细节: 0
AI商业部署信号: 0
AI完整性: 8
AI摘要: "Amazon SageMaker Unified Studio 推出由 AWS Glue Data Quality 驱动的数据剖析与异常检测功能，可对目录表静态数据和 Visual ETL 动态数据生成统计画像并追踪变化。"
AI摘要模型: "ali-deepseek-v4-flash"
AI摘要时间: "2026-09-07T02:13:22.638Z"
采集批次: "2026年8月21日9点50分40秒"
采集批次ID: "20260821-095040-035"
去重键: "https://aws.amazon.com/cn/about-aws/whats-new/2026/05/smus-data-profiling"
---

Amazon SageMaker Unified Studio now supports data profiling and anomaly detection, powered by AWS Glue Data Quality. Data stewards, engineers and analysts can generate statistical profiles of their data to understand its shape and completeness, and track how these statistics change over time. Anomaly detection helps identify when data points drift from historical patterns without requiring predefined thresholds or custom rules. These capabilities are available for both data at rest in catalog tables and data in transit within Visual ETL jobs.

With this launch, a dedicated Data profile tab on catalog tables provides on-demand and scheduled profiling that computes dataset-level and column-level statistics. As profile history accumulates, anomaly detection builds a baseline of expected behavior and flags data points that fall outside the predicted range. This is particularly useful when you may not be aware of specific thresholds, or when expected values change over time and fixed rules could become stale. For data in transit, the same profiling statistics and anomaly detection are available on the results page of any Visual ETL job with an Evaluate Data Quality transform.

This feature is available in all AWS Regions where Amazon SageMaker Unified Studio is available. To learn more, visit the [Amazon SageMaker Unified Studio documentation.](https://docs.aws.amazon.com/sagemaker-unified-studio/latest/userguide/data-profiling-catalog.html)