Gemini in Chrome Adds Select from Screen for Faster Image and Page Analysis
Gemini in Chrome Adds Select from Screen for Faster Image and Page Analysis
Chrome 版 Gemini 新增“屏幕选择”功能，实现更快速的图像与页面分析
Google has expanded Gemini in Chrome with a desktop workflow that lets users send a selected part of a web page directly to Gemini. Called Select from screen, the feature is designed for moments when a full page is not the relevant context: a user can draw a box around particular text, an image, or a mixed section of page content and ask Gemini to analyze or act on it in Chrome’s side panel. Google 已扩展了 Chrome 版 Gemini 的桌面工作流，允许用户将网页的选定部分直接发送给 Gemini。该功能被称为“屏幕选择”（Select from screen），专为那些无需整页上下文的场景而设计：用户可以框选特定的文本、图像或混合页面内容，并要求 Gemini 在 Chrome 侧边栏中对其进行分析或处理。
The change makes Gemini more closely embedded in everyday browser work. Rather than manually describing what is on a page or switching between tools, users can identify the exact on-screen material they want Gemini to consider. For teams that regularly research products, review creative assets, compare information, or work from web-based documents, that can make AI assistance more immediate. Its usefulness will still depend on whether Gemini in Chrome is enabled for the user and, for managed environments, how administrators configure access. 这一变化使 Gemini 更紧密地融入了日常浏览器工作。用户无需手动描述页面内容或在不同工具间切换，即可精准指定希望 Gemini 处理的屏幕素材。对于经常进行产品调研、审查创意资产、比较信息或处理网页文档的团队而言，这能让 AI 辅助变得更加即时。该功能的实用性仍取决于用户是否启用了 Chrome 版 Gemini，以及在受管理的环境中，管理员如何配置访问权限。
How Select from screen works
“屏幕选择”功能的工作原理
Google’s official instructions for sharing specific parts of a screen with Gemini in Chrome describe a straightforward process. Users open the Gemini side panel in Chrome, choose Select from screen, then draw around the area they want to share. The chosen content is sent to Gemini as the basis for the next interaction. The important distinction is that the feature is not limited to a single content type. Google says the selected region can contain text and/or images. That gives users a more precise way to supply context from a web page without treating the entire page as the prompt. Google 关于在 Chrome 版 Gemini 中共享屏幕特定部分的官方说明描述了一个简单的流程：用户打开 Chrome 中的 Gemini 侧边栏，选择“屏幕选择”，然后框选想要共享的区域。所选内容将作为下一次交互的基础发送给 Gemini。值得注意的是，该功能并不局限于单一内容类型。Google 表示，选定区域可以包含文本和/或图像。这为用户提供了一种更精确的方式来提供网页上下文，而无需将整个页面作为提示词。
| Workflow element | General Gemini interaction in Chrome | Select from screen |
|---|---|---|
| 工作流要素 | Chrome 版 Gemini 常规交互 | 屏幕选择 (Select from screen) |
| Context provided | User supplies a request in the Chrome side panel | User selects a defined region of a web page for Gemini |
| 提供的上下文 | 用户在 Chrome 侧边栏中输入请求 | 用户为 Gemini 选择网页的特定区域 |
| Content types | Depends on the interaction and context available | Selected text, images, or a region containing both |
| 内容类型 | 取决于交互和可用上下文 | 选定的文本、图像或包含两者的区域 |
| Selection method | No region-selection step | Draw a bounding box around the relevant content |
| 选择方式 | 无区域选择步骤 | 在相关内容周围绘制边框 |
Why the workflow matters
为什么该工作流很重要
The value is context selection, not simply another way to open an AI chatbot. A marketing manager could isolate an image or page section when preparing a brief. A buyer could select product details while comparing suppliers. A support or operations employee could share a relevant portion of a web interface when seeking help interpreting what they see. These are examples of potential uses, not promises that Gemini will produce an accurate or complete answer in every case. Users should still review outputs before using them in customer-facing, financial, legal, or operational decisions. The browser feature reduces the friction of providing context, but it does not remove the need for human judgment. 其价值在于上下文的选择，而不仅仅是打开 AI 聊天机器人的另一种方式。营销经理在准备简报时可以截取图像或页面部分；采购人员在比较供应商时可以选中产品详情；支持或运营人员在寻求帮助以解读界面信息时，可以共享网页界面的相关部分。这些只是潜在用途的示例，并不保证 Gemini 在任何情况下都能提供准确或完整的答案。用户在将输出结果用于面向客户、财务、法律或运营决策之前，仍应进行审核。该浏览器功能降低了提供上下文的门槛，但并未消除对人类判断的需求。
Access, administration, and rollout considerations
访问、管理与推广注意事项
Select from screen is part of Google’s wider Gemini in Chrome initiative, which also includes deeper connections with Google services such as Calendar, Gmail, Maps, and YouTube. Google has also signaled further expansion of the broader feature family, including regional availability and additional capabilities such as editing images found on the web. That broader rollout matters because availability may not be identical for every Chrome user. The supplied documentation confirms the Select from screen workflow, but it does not establish a universal price, a single worldwide availability date, or that every related Gemini in Chrome feature is included with every account tier. “屏幕选择”是 Google 更广泛的 Chrome 版 Gemini 计划的一部分，该计划还包括与日历、Gmail、地图和 YouTube 等 Google 服务的深度连接。Google 还表示将进一步扩展该功能系列，包括区域可用性以及诸如编辑网页图像等额外功能。这种更广泛的推广非常重要，因为并非所有 Chrome 用户的可用性都相同。现有文档确认了“屏幕选择”的工作流，但并未设定统一的价格、全球统一的发布日期，也未说明所有相关的 Chrome 版 Gemini 功能都包含在每个账户层级中。
Google has indicated that some capabilities may be limited by rollout phase, region, or Google AI Pro and Ultra subscription access. For Workspace domains and other managed Chrome environments, administrators may also control whether Gemini in Chrome is available. Before building a team process around it, organizations should check: Google 指出，某些功能可能会受到推广阶段、地区或 Google AI Pro 和 Ultra 订阅权限的限制。对于 Workspace 域和其他受管理的 Chrome 环境，管理员还可以控制是否启用 Chrome 版 Gemini。在围绕该功能建立团队流程之前，组织应检查：
- Whether Gemini in Chrome is enabled in Chrome’s AI innovations settings.
- Chrome 的 AI 创新设置中是否启用了 Chrome 版 Gemini。
- Whether account, region, subscription, or rollout conditions affect the intended feature.
- 账户、地区、订阅或推广条件是否影响了预期的功能。
- Whether Workspace or other administrative controls permit Gemini in Chrome for their users.
- Workspace 或其他管理控制项是否允许用户使用 Chrome 版 Gemini。
- What internal guidance is appropriate before staff share sensitive page content with an AI assistant.
- 在员工与 AI 助手共享敏感页面内容之前，应制定何种内部指导方针。
Practical ways to test it
实际测试方法
The most useful first test is a repeatable task with a clear expected outcome. For example, a team could select a product comparison area and ask Gemini to identify the differences shown, or select a visual and nearby copy to help generate a draft internal summary. This reveals whether the feature saves time in a real workflow rather than merely producing an interesting demonstration. Keep the evaluation narrow. Compare the time required to prepare a prompt manually with the time required to select the relevant region and refine Gemini’s response. Also note when the selected content lacks the context needed for a reliable answer. A tightly cropped region may be efficient, but surrounding page information can sometimes change its meaning. 最有用的初步测试是针对具有明确预期结果的可重复任务。例如，团队可以选择产品比较区域并要求 Gemini 识别差异，或者选择一张图片及其附近的文案来帮助生成内部摘要草稿。这能揭示该功能是在实际工作流中节省了时间，还是仅仅产生了一个有趣的演示。评估范围要小。比较手动准备提示词所需的时间与选择相关区域并优化 Gemini 回复所需的时间。同时注意选定内容何时缺乏可靠回答所需的上下文。裁剪过紧的区域可能很高效，但周围的页面信息有时会改变其含义。
AI features in the browser can reduce repetitive research and handoff work, but the gains come from choosing tasks where the source content is suitable to share and the output can be checked quickly. Through Scalevise’s practical AI consultancy, businesses can identify browser-based AI tasks that reduce manual work, test them against real processes, and set clear usage rules before adoption spreads across a team. Request a consultation to turn promising AI features into a measurable workflow improvement. 浏览器中的 AI 功能可以减少重复性的研究和交接工作，但收益来自于选择那些源内容适合共享且输出结果可快速核对的任务。通过 Scalevise 的实用 AI 咨询服务，企业可以识别能够减少手动工作的基于浏览器的 AI 任务，针对实际流程进行测试，并在团队推广前设定明确的使用规则。申请咨询，将有前景的 AI 功能转化为可衡量的流程改进。
Frequently Asked Questions
常见问题解答
What is Select from screen in Gemini in Chrome? 什么是 Chrome 版 Gemini 中的“屏幕选择”？ Select from screen is a Gemini in Chrome option that lets a user draw around a specific region of a web page and send that selected content to Gemini through Chrome’s side panel. “屏幕选择”是 Chrome 版 Gemini 的一个选项，允许用户框选网页的特定区域，并通过 Chrome 侧边栏将选定内容发送给 Gemini。
Can Select from screen include images and text? “屏幕选择”可以包含图像和文本吗？ Yes. Google’s documentation says the selected area can include text, images, or both. 可以。Google 的文档显示，选定区域可以包含文本、图像或两者兼有。
How do users access the feature? 用户如何访问该功能？ Users open the Gemini side panel in Chrome, choose Select from screen, and draw around the content area they want to share with Gemini. 用户打开 Chrome 中的 Gemini 侧边栏，选择“屏幕选择”，然后框选想要与 Gemini 共享的内容区域。
Is Gemini in Chrome available to every browser user? 所有浏览器用户都能使用 Chrome 版 Gemini 吗？ (Note: The original text was cut off here.) （注：原文此处截断。）