azure-anomaly-detector

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Azure AI Anomaly Detector Skill

Azure AI Anomaly Detector技能

This skill provides expert guidance for Azure AI Anomaly Detector. Covers troubleshooting, best practices, architecture & design patterns, limits & quotas, configuration, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
本技能为Azure AI Anomaly Detector提供专家指导,涵盖故障排查、最佳实践、架构与设计模式、限制与配额、配置以及部署。它结合了本地快速参考内容与远程文档获取能力。

How to Use This Skill

如何使用本技能

IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g.,
L35-L120
), use
read_file
with the specified lines. For categories with file links (e.g.,
[security.md](security.md)
), use
read_file
on the linked reference file
IMPORTANT for Agent: If
metadata.generated_at
is more than 3 months old, suggest the user pull the latest version from the repository. If
mcp_microsoftdocs
tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
  • Preferred: Use
    mcp_microsoftdocs:microsoft_docs_fetch
    with query string
    from=learn-agent-skill
    . Returns Markdown.
  • Fallback: Use
    fetch_webpage
    with query string
    from=learn-agent-skill&accept=text/markdown
    . Returns Markdown.
Agent注意事项:使用下方的分类索引定位相关章节。对于带有行范围的分类(例如
L35-L120
),使用
read_file
读取指定行内容。对于带有文件链接的分类(例如
[security.md](security.md)
),使用
read_file
读取链接的参考文件。
Agent注意事项:如果
metadata.generated_at
已超过3个月,建议用户从仓库拉取最新版本。如果
mcp_microsoftdocs
工具不可用,建议用户安装该工具:安装指南
本技能需要网络访问权限来获取文档内容:
  • 首选方式:使用
    mcp_microsoftdocs:microsoft_docs_fetch
    并携带查询字符串
    from=learn-agent-skill
    ,返回Markdown格式内容。
  • 备用方式:使用
    fetch_webpage
    并携带查询字符串
    from=learn-agent-skill&accept=text/markdown
    ,返回Markdown格式内容。

Category Index

分类索引

CategoryLinesDescription
TroubleshootingL34-L39Diagnosing and fixing Anomaly Detector issues, including multivariate API error codes, model training/detection failures, data format problems, and common service or configuration errors.
Best PracticesL40-L45Guidance on preparing data, tuning parameters, interpreting results, and designing workflows for effective use of univariate and multivariate Azure Anomaly Detector APIs.
Architecture & Design PatternsL46-L50Designing predictive maintenance solutions using Multivariate Anomaly Detector, including data preparation, model setup, and architecture patterns for monitoring complex equipment.
Limits & QuotasL51-L56Details on Anomaly Detector regional endpoints, usage constraints, request/throughput limits, quotas, and how these caps affect model training and inference.
ConfigurationL57-L61How to configure and tune Anomaly Detector Docker containers, including environment variables, resource limits, logging, networking, and runtime behavior settings.
DeploymentL62-L67How to package and run Anomaly Detector in containers: Docker setup, Azure Container Instances deployment, and IoT Edge module deployment and configuration.
分类行范围描述
故障排查L34-L39诊断并修复Anomaly Detector问题,包括多变量API错误代码、模型训练/检测失败、数据格式问题以及常见服务或配置错误。
最佳实践L40-L45关于数据准备、参数调优、结果解读以及工作流设计的指导,以有效使用单变量和多变量Azure AI Anomaly Detector API。
架构与设计模式L46-L50使用Multivariate Anomaly Detector设计预测性维护解决方案,包括数据准备、模型设置以及复杂设备监控的架构模式。
限制与配额L51-L56Anomaly Detector区域端点、使用约束、请求/吞吐量限制、配额的详细信息,以及这些限制对模型训练和推理的影响。
配置L57-L61如何配置和调优Anomaly Detector Docker容器,包括环境变量、资源限制、日志记录、网络和运行时行为设置。
部署L62-L67如何在容器中打包和运行Anomaly Detector:Docker设置、Azure Container Instances部署以及IoT Edge模块的部署与配置。

Troubleshooting

故障排查

Best Practices

最佳实践

Architecture & Design Patterns

架构与设计模式

TopicURL
Design predictive maintenance with Multivariate Anomaly Detectorhttps://learn.microsoft.com/en-us/azure/ai-services/anomaly-detector/concepts/multivariate-architecture
主题链接
使用Multivariate Anomaly Detector设计预测性维护方案https://learn.microsoft.com/en-us/azure/ai-services/anomaly-detector/concepts/multivariate-architecture

Limits & Quotas

限制与配额

Configuration

配置

Deployment

部署