데이터·AI 스킬

Add text and image moderation to Python applications using Azure AI Content Safety. Analyze harmful content by category and severity, manage custom text blocklists, and use the results to apply thresholds for user submissions or AI outputs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check user-submitted text and images
• Analyze AI outputs before displaying them
• Manage custom lists of blocked terms

Create Python agents on Azure AI Foundry that retain conversation context and use multiple tools. The skill covers code execution, file and web search, external tool connections, streaming responses, and outputs organized into defined fields.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build an agent that retains conversation context
• Combine code execution with file and web search
• Connect external tools through MCP

Build text and image moderation features in Java with Azure AI Content Safety. The skill guides category-based harm analysis, severity scoring, and custom blocklists for checking content against terms you specify.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check text for harmful content
• Analyze uploaded images for harmful content
• Manage custom blocklists

Build image analysis features in Java with Azure AI Vision. Add image descriptions, OCR for reading text in images, object and people detection, content tags, and suggested crop regions for thumbnails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add image descriptions to a Java application
• Extract text from document images
• Detect objects and people with their locations

Build anomaly detection features in Java for time-series data, meaning measurements recorded over time. Use Azure AI Anomaly Detector to check individual signals, analyze related signals together, detect trend changes, and manage trained models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find anomalies across a historical time series
• Check whether the latest measurement is unusual
• Detect changes in a time-series trend

Implement document extraction in Java with Azure AI Document Intelligence. Read text, tables, and fields from PDFs, invoices, receipts, and IDs, or build custom models and classifiers that identify document types.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extract text and tables from PDFs
• Read fields from invoices and receipts
• Build extraction models for custom document formats

Implement text analysis in Python with Azure AI Language. Covers sentiment detection, extracting names and key phrases, identifying languages, masking personal information, and extracting medical terms, with examples for batch processing and asynchronous clients.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Analyze sentiment and specific opinions in customer reviews
• Detect and mask personal information in text
• Extract names, organizations, and key phrases from documents

Manage Azure AI Foundry project resources from Java. This skill guides authentication and specialized clients for connections, datasets, model deployments, search indexes that organize searchable content, and evaluations used to assess AI models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• List project connections and model deployments
• Upload documents and manage datasets
• Create or update search indexes

Build .NET voice assistants that exchange audio with Azure AI in real time. This skill guides session setup, speech turn detection, audio and text responses, and function calls that connect conversations to external services.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a .NET voice assistant
• Add spoken responses to a chatbot
• Connect voice conversations to external services

Build Azure OpenAI features into .NET applications with guidance on authentication, chat, image generation, and audio processing. Examples also cover search integration and structured responses that follow a specified data format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding streaming chat to a .NET application
• Building answers grounded in Azure AI Search results
• Integrating image generation and audio transcription

Turn existing KQL or IRQL query results into relationship diagrams in Kusto Explorer. Generates mappings for entities and connections, adds icons, and composes stored functions to group nodes or add available information to the graph.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Visualize relationships in authentication query results
• Map email senders, messages, and recipients
• Group graph nodes that share a property

Turn tabular Kusto query results into graphs that represent entities and their relationships. Generate KQL, Kusto's query language, to find patterns, shortest paths, and connected groups, with reusable graph models and table exports also covered.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing relationships between users and hosts in authentication logs
• Finding shortest paths to critical assets
• Identifying connected groups in network data

Write, debug, and review KQL queries for log analysis and data exploration. Get guidance on joins, data types, dates, and memory use to address common errors and keep query results manageable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Write KQL queries to aggregate logs
• Fix query errors involving joins or data types
• Review queries that use too much memory

Build document analysis into .NET applications using Azure AI Document Intelligence. Extract text, tables, and typed fields from common documents, then create and manage custom models or classifiers for specialized forms and document categories.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting vendors, totals, and line items from invoices
• Reading merchant names, totals, and dates from receipts
• Retrieving PDF text and table cell positions

Transform live camera feeds into colorized depth maps that show how near or far objects are. Choose a depth-only view, an overlay, or a side-by-side comparison to inspect spatial layout and activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Viewing activity through a depth-only camera feed
• Checking the spatial layout of a camera scene
• Comparing original footage with estimated depth

Manage labeled datasets in Aegis Annotation Studio, including creating and deleting datasets, saving and loading annotations, and organizing labels. Export annotations in COCO format, a standard dataset structure, or upload datasets to Kaggle.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating and organizing annotation datasets
• Saving and loading annotations for individual frames
• Exporting labeled data in COCO format

Detect people, cars, pets, and other objects in live camera frames using a Google Coral Edge TPU through Windows WSL2. Choose from 80 object categories and adjust detection confidence, processing rate, and input resolution.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting people and cars in live camera frames
• Limiting detection to selected object categories
• Adjusting processing rate and resolution

Detect people, cars, and other objects in Aegis camera frames using OpenVINO inside Docker. Adjust detection settings for Intel GPUs, NCS2 hardware, or a CPU, and return object locations and confidence scores.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detect people or cars in Aegis camera images
• Configure object detection for Intel hardware or a CPU
• Adjust detection thresholds, frame rates, and resolution

Fine-tune YOLO26 object detection models with custom labeled image datasets in COCO format. Track training progress, validate detection accuracy, export for the available hardware, and optionally replace the active detection model in Aegis with the trained version.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Train an object detector on custom labeled images
• Monitor training progress and detection accuracy
• Export a trained model for the available hardware

Create training datasets for custom object detection models by labeling images and video frames. Use AI-suggested boxes, click-based object masks, and tracking, review the annotations manually, and export the dataset in COCO, YOLO, or VOC format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating training data for custom object detection
• Reviewing and correcting AI-detected object boxes
• Labeling object regions with SAM2

Detect people, cars, pets, and other objects in live camera frames using a Google Coral Edge TPU on macOS or Linux. Select from 80 object categories and receive results with confidence scores and object locations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting people and pets in live camera frames
• Limiting detection to selected object categories
• Adjusting processing rate and resolution

Select objects in video frames with clicks or boxes using Segment Anything 2. Create masks that mark object areas, propagate selections across a clip, and support labeling and dataset creation within Annotation Studio.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create object masks by clicking video frames
• Refine selections with points or boxes
• Track a selected object across a clip

Evaluate vision-language models, AI that interprets images and text, on smart home video anomaly detection. Sample multiple frames from clips across seven categories and generate HTML reports with accuracy metrics, error breakdowns, and model comparisons.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Compare models for home camera anomaly detection
• Evaluate security or wildlife clips separately
• Run a quick evaluation on 10 videos

Detect people, vehicles, animals, and other objects in live camera feeds, with boxes showing their positions, labels, and confidence scores. Adjust target classes, model size, and processing frequency to suit the available hardware.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Detecting people and vehicles in live camera feeds
• Limiting detection to selected object classes
• Balancing detection accuracy and processing load