Bigquery Ai Ml

作者 google55b4e13eba6d無授權條款收錄於 2026年10月8日更新於 2026年10月8日

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity, summarize content, translate language, evaluate models, filter by semantic conditions, measure the causal effect of an intervention, compute correlations between columns, detect change points or structural breaks, extract trend or seasonality components, or leverage generative AI capabilities in BigQuery. Do not use for general BigQuery dataset, table, or job management requests.

精選僅含說明Data & Analytics
AI 產生的概覽

指導撰寫使用 BigQuery 內建 AI 與機器學習函式的 SQL,用於預測、異常偵測、分類和語意搜尋。

功能
此技能為在 SQL 查詢中使用 BigQuery 內建 AI 與機器學習函式提供參考指引,包括 AI.FORECAST、AI.KEY_DRIVERS、AI.DETECT_ANOMALIES、AI.GENERATE、AI.CLASSIFY、AI.SEARCH 和 ML.CORRELATION。內容涵蓋時間序列預測、異常與變化點偵測、關鍵驅動因素與貢獻分析、趨勢與季節性擷取、文字分類、語意與向量搜尋、嵌入、相似度、模型評估以及因果效應衡量。其產出是 SQL 查詢指引,而非產生的檔案或指令碼。
適用情境
當需要撰寫執行機器學習或生成式 AI 分析的 BigQuery SQL 時使用,例如預測、離群值偵測、語意搜尋或文字分類。它不適用於一般 BigQuery 資料集、資料表或工作管理請求。
執行需求
需要 BigQuery 及其內建 AI 與機器學習函式,對於生成式和遠端模型函式還需要 Vertex AI 整合。僅為說明文件,不包含指令碼。

BigQuery AI & ML

BigQuery integrates with Vertex AI to provide powerful machine learning and generative AI capabilities directly within SQL queries using built-in functions like AI.FORECAST, AI.KEY_DRIVERS, AI.DETECT_ANOMALIES, and AI.GENERATE.

Reference Directory

  • Functions Reference:

    • AI.AGG: ai_agg.md [blocked] - Multi-row semantic aggregation and summarization.
    • AI.CAUSAL_EFFECT: ai_causal_effect.md [blocked] - Quantifies the impact of an intervention on a time series.
    • AI.CLASSIFY: ai_classify.md [blocked] - Classify text.
    • AI.DETECT_ANOMALIES: ai_detect_anomalies.md [blocked] - Detect anomalies.
    • AI.EVALUATE: ai_evaluate.md [blocked] - Evaluate models.
    • AI.FORECAST: ai_forecast.md [blocked] - Time-series forecasting.
    • AI.GENERATE: ai_generate.md [blocked] - Generate text using LLMs.
    • AI.GENERATE_EMBEDDING: ai_generate_embedding.md [blocked] - Generate embeddings.
    • AI.GENERATE_TABLE: ai_generate_table.md [blocked] - Table-valued AI generation.
    • AI.IF: ai_if.md [blocked] - Evaluate semantic conditions.
    • AI.KEY_DRIVERS: ai_key_drivers.md [blocked] - Identifies key drivers, this is a TVF.
    • AI.SCORE: ai_score.md [blocked] - Score data.
    • AI.SEARCH: ai_search.md [blocked] - Semantic search.
    • AI.SIMILARITY: ai_similarity.md [blocked] - Semantic similarity.
    • Remote Models: remote_models.md [blocked] - Working with remote models (Vertex AI).
    • CONTRIBUTION_ANALYSIS: ml_contribution_analysis.md [blocked]
      • Finds contributing factors, key drivers of change. Requires creating a MODEL entity.
    • ML.CORRELATION: ml_correlation.md [blocked] - Calculates correlation between columns, optionally sliced by dimensions.
    • ML.DETECT_CHANGE_POINTS: ml_detect_change_points.md [blocked] - Detects structural breaks or sustained shifts in a time series.
    • ML.SEASONALITY: ml_seasonality.md [blocked] - Extracts seasonal components from a time series.
    • ML.TREND: ml_trend.md [blocked] - Extracts the long-term trend component from a time series.
    • VECTOR_SEARCH: vector_search.md [blocked] - Vector search best practices.

Related Skills

  • BigQuery Basics Skill: SKILL.md file for core BigQuery concepts, resource management, CLI, and client libraries.

來源與署名

來源:google/skills位於skills/cloud/bigquery-ai-ml提交55b4e13

授權條款: 無授權條款

內容歸原作者所有。SourceWeft 從公開儲存庫中收錄這些內容。

檢舉或申請下架

更多來自 google/skills 的技能

Dpop Adoption

google

精選

Implement and debug OAuth 2.0 DPoP (RFC 9449) refresh token sender-constraining for WebCrypto, Node.js ES6, and browser runtimes integrating with Google's OAuth platform. Use when configuring non-extractable asymmetric key pairs (P-256), generating DPoP Proof JWTs for authorization code exchange and token refresh, or handling 400 use_dpop_nonce challenge retry loops at oauth2.googleapis.com/token. Don't use for unconstrained OAuth 2.0 flows (where refresh tokens are not bound to a client key pair), or for Google Cloud IAM / service account authentication.

待分類2026年10月8日

Finding Google Skills

google

精選

Google platform decision and setup guidance, loaded on demand from Google's skill catalog. Use when a developer is choosing or setting up part of their stack, such as where to run a service, a database, storage, messaging, authentication, analytics, ads, or AI model serving, and a Google product is a reasonable candidate - whether or not a vendor is named - or when a request names a Google product or API. Brings in the matching Google skill so the answer can weigh Google options, their trade-offs, and when they are not the right fit. Skip when the stack is already settled on another provider and no Google product is named, or the task involves no platform choice.

待分類2026年10月8日

Spanner Basics

google

精選

指導 Google Cloud Spanner 的執行個體與資料庫管理、結構定義設計、查詢與效能診斷。

Data & Analytics2026年10月8日

Secops Triage

google

精選

引導 SOC 分析師對 Google SecOps 安全警示進行分診,從調查到結案或升級。

Security2026年10月8日

Secops Investigate

google

精選

指導 SOC 分析師在 Google SecOps 中使用 UDM 查詢與時間軸進行深入的安全事件與實體調查。

Security2026年10月8日

Secops Hunt

google

精選

指導在 Google SecOps 中使用 UDM 查詢、IoC 回溯、普遍性與異常分析進行主動威脅狩獵。

Security2026年10月8日