为满足 Apple App Store 数据披露要求做准备
使用集合让一切井井有条
根据您的偏好保存内容并对其进行分类。
Apple 要求在 App Store 上发布应用的开发者披露有关其应用数据使用情况的特定信息。Apple 宣布，从 2020 年 12 月 8 日起，开发者必须为新应用及更新的应用提供这类披露信息。本文档包含可能需要根据 Apple 的指南进行披露的机器学习套件库行为。
本页面仅列出每个机器学习套件 iOS SDK 的最新版本收集的数据。
收集的数据
所有功能中收集的数据
| 数据
|
默认情况下，机器学习套件 SDK 会收集...
|
| 设备信息
|
设备信息（例如制造商、型号、操作系统版本和 build）以及可用的机器学习硬件加速器。用于诊断和使用情况分析。 |
| 应用信息
|
软件包 ID 和应用版本。用于诊断和使用情况分析。
|
| 设备或其他标识符
|
并非用于唯一标识用户或实体设备的每次安装标识符。用于诊断和使用情况分析。
|
| 性能指标
|
性能指标（例如延迟时间）。用于诊断和使用情况分析。 |
| API 配置
|
API 配置（例如图片格式和分辨率）。用于诊断和使用情况分析。 |
| 事件类型
|
事件类型（例如功能初始化、模型下载、检测、资源发布）。用于诊断和使用情况分析。
|
| 错误代码
|
特征事件（如特征初始化、模型下载、检测、资源发布）的错误代码。用于诊断和使用情况分析。 |
自定义对象检测和图片标签
MLKitObjectDetectionCustom
MLKitImageLabelingCustom
翻译
MLKitTranslate
实体提取和数字手写识别
MLKitEntityExtraction
MLKitDigitalInkRecognition
智能回复
MLKitSmartReply
语言 ID
MLKitLanguageID
如未另行说明，那么本页面中的内容已根据知识共享署名 4.0 许可获得了许可，并且代码示例已根据 Apache 2.0 许可获得了许可。有关详情，请参阅 Google 开发者网站政策。Java 是 Oracle 和/或其关联公司的注册商标。
最后更新时间 (UTC)：2025-07-25。
[null,null,["最后更新时间 (UTC)：2025-07-25。"],[[["\u003cp\u003eStarting December 8, 2020, Apple requires developers to disclose data collection practices of their apps, including those using ML Kit.\u003c/p\u003e\n"],["\u003cp\u003eML Kit for iOS collects device information, application details, performance metrics, and other data for diagnostics and usage analytics across all features.\u003c/p\u003e\n"],["\u003cp\u003eSpecific ML Kit features, like custom object detection or translation, may collect additional data such as model information or configured languages.\u003c/p\u003e\n"],["\u003cp\u003eSome ML Kit features utilize Firebase services, requiring further data disclosure as outlined in Firebase documentation.\u003c/p\u003e\n"],["\u003cp\u003eDevelopers should review the detailed data collection information provided for each ML Kit feature to ensure accurate and complete disclosure to Apple.\u003c/p\u003e\n"]]],["Apple mandates developers disclose app data usage, effective December 8, 2020. The ML Kit iOS SDK collects device, application, and identifier information, performance metrics, API configuration, event types, and error codes, for diagnostics and usage analytics. Custom object detection and image labeling features also collect model details. Translate, Smart Reply features collect configured or identified languages. Entity extraction and digital ink recognition also gather configured languages. Specific features may use Firebase for additional functions.\n"],null,["# Prepare for Apple’s App Store data disclosure requirements\n\nApple requires developers publishing apps on the App Store to disclose\n[certain information](https://developer.apple.com/app-store/app-privacy-details/)\nregarding their apps' data use. Apple has\n[announced](https://developer.apple.com/news/?id=vlj9jty9) that these\ndisclosures are required for new apps and app updates starting December 8, 2020.\nThis document contains ML Kit library behaviors that could require disclosure\naccording to Apple's guidelines.\n\nThis page lists the data collected by only\n[the latest version](https://developers.google.com/ml-kit/release-notes) of each\nML Kit iOS SDK.\n\nCollected data\n--------------\n\n### Data collected in all features\n\n|-----------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------|\n| **Data** | **By default, the ML Kit SDK collects...** |\n| Device information | Device information (such as manufacturer, model, OS version and build) and available ML hardware accelerators. Used for diagnostics and usage analytics. |\n| Application information | Bundle ID and app versions. Used for diagnostics and usage analytics. |\n| Device or other identifiers | Per-installation identifiers that are not intended to uniquely identify a user or physical device. Used for diagnostics and usage analytics. |\n| Performance metrics | Performance metrics (such as latency). Used for diagnostics and usage analytics. |\n| API configuration | API configuration (such as image format and resolution). Used for diagnostics and usage analytics. |\n| Event type | Event type (such as feature initializations, model downloads, detection, resource releases). Used for diagnostics and usage analytics. |\n| Error codes | Error code for feature events (such as feature initializations, model downloads, detection, resource releases). Used for diagnostics and usage analytics. |\n\n### Extra data collected in specific features\n\n#### Custom object detection and image labeling\n\n`MLKitObjectDetectionCustom` \n\n`MLKitImageLabelingCustom`\n\n- If you are using these libraries with custom models, the following data is collected:\n - Name, version, and URI/URL of the machine learning model for diagnostics\n- If you are using [Firebase Model Deployment](https://firebase.google.com/docs/ml/manage-hosted-models) with *`MLKitLinkFirebase`* to remotely host a custom model, refer to the [Firebase ML model downloader](https://firebase.google.com/docs/ios/app-store-data-collection#firebasemlmodeldownloader) and [Firebase installations](https://firebase.google.com/docs/ios/app-store-data-collection#installations) sections in [Prepare for Apple Store data disclosure requirements](https://firebase.google.com/docs/ios/app-store-data-collection).\n\n#### Translate\n\n`MLKitTranslate`\n\n- Configured source and destination languages. Used for diagnostics and usage analytics.\n- ML Kit uses *Firebase remote config* and *Firebase installations* for remote configuration diagnostics. Please refer to the [Firebase remote config](https://firebase.google.com/docs/ios/app-store-data-collection#remote-config) and [Firebase installations](https://firebase.google.com/docs/ios/app-store-data-collection#installations) sections in [Prepare for Apple Store data disclosure requirements](https://firebase.google.com/docs/ios/app-store-data-collection).\n\n#### Entity extraction and digital ink recognition\n\n`MLKitEntityExtraction` \n\n`MLKitDigitalInkRecognition`\n\n- Configured languages. Used for diagnostics and usage analytics.\n\n#### Smart reply\n\n`MLKitSmartReply`\n\n- Identified languages. SmartReply internally uses language identification to only respond to specific languages. Used for diagnostics and usage analytics.\n- ML Kit uses *Firebase remote config* and *Firebase installations* for remote configuration diagnostics. Please refer to the [Firebase remote config](https://firebase.google.com/docs/ios/app-store-data-collection#remote-config) and [Firebase installations](https://firebase.google.com/docs/ios/app-store-data-collection#installations) sections in [Prepare for Apple Store data disclosure requirements](https://firebase.google.com/docs/ios/app-store-data-collection).\n\n#### Language ID\n\n`MLKitLanguageID`\n\n- Identified languages. Used for diagnostics and usage analytics."]]
