> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features.md).

# 功能

功能是插件的 AI 驱动能力模块。每个功能都会针对特定用途连接到 Convai——执行场景内行为、表达情绪、跨会话记住玩家、跟随编写好的叙事图，或通过摄像头感知世界。每个部分都包含概念概览、快速开始、Blueprint 属性参考、使用示例和故障排查指南。

选择一个功能开始：

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>角色动作</strong><br>让 Convai 返回结构化的动作序列，由你的 Blueprint 事件处理器执行——移动到物体、跟随玩家，或运行任何自定义行为。</td><td><a href="/pages/46d3b8351132c46e6470ee20811d82cf5cae7051">/pages/46d3b8351132c46e6470ee20811d82cf5cae7051</a></td></tr><tr><td><strong>动态上下文</strong><br>在不中断连接的情况下，于会话中途将实时运行状态——生命值、库存、区域、事件——推送到角色的上下文窗口中。</td><td><a href="/pages/f1aab12e2433cc2eba9f8b33106fed6d232fe3de">/pages/f1aab12e2433cc2eba9f8b33106fed6d232fe3de</a></td></tr><tr><td><strong>情绪</strong><br>将 Convai 的情绪信号转换为任意骨骼角色上各情绪对应的 blendshape 权重和评分。</td><td><a href="/pages/dac8d878741e85925d7a212fef1afa2b99e74a9d">/pages/dac8d878741e85925d7a212fef1afa2b99e74a9d</a></td></tr><tr><td><strong>长期记忆</strong><br>通过 Speaker ID 和会话连续性为角色提供跨会话记忆——角色会随着时间记住单个玩家、事实和过往互动。</td><td><a href="/pages/19f4740b1fd265f1b629850b246b7b0621411221">/pages/19f4740b1fd265f1b629850b246b7b0621411221</a></td></tr><tr><td><strong>叙事设计</strong><br>围绕编写好的故事图来组织角色行为——章节定义目标和语气，触发器推进叙事，模板键注入实时游戏数据。</td><td><a href="/pages/c50f2cbde2d775fd6a1147c0ab6bbcf15218f3a6">/pages/c50f2cbde2d775fd6a1147c0ab6bbcf15218f3a6</a></td></tr><tr><td><strong>场景元数据</strong><br>为世界中的 Actor 添加标签 <code>UConvaiObjectComponent</code> ，这样 Convai 角色就能知道场景中存在哪些物体，并在对话中按名称引用它们。</td><td><a href="/pages/ae13b29a517504598ad569023c6483ae28a3af7b">/pages/ae13b29a517504598ad569023c6483ae28a3af7b</a></td></tr><tr><td><strong>视觉</strong><br>将场景帧从捕获组件流式传输到 Convai，使角色能够实时感知并讨论玩家所看到的内容。</td><td><a href="/pages/efe0ea28574973991aa04b83a3d8227caa960b67">/pages/efe0ea28574973991aa04b83a3d8227caa960b67</a></td></tr><tr><td><strong>注视注意力</strong><br>使用玩家的视线来决定角色聚焦于哪个场景物体——持续注视会通过可配置的停留计时器将物体提升为主动注意目标。</td><td><a href="/pages/4a5f4bca34572e7102d0b723f97623ed14ebc472">/pages/4a5f4bca34572e7102d0b723f97623ed14ebc472</a></td></tr><tr><td><strong>口型同步</strong><br>使用以下方式驱动嘴部和面部 blendshape，使其与 Convai 语音同步 <code>UConvaiFaceSyncComponent</code> ——支持 MetaHuman、ARKit、CC4 和 viseme 目标。</td><td><a href="/pages/cc7d248786c91571b1e6761c7044cd749219d47a">/pages/cc7d248786c91571b1e6761c7044cd749219d47a</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unreal-engine-plugin/features.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.