> 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-unity-sdk/core-concepts.md).

# 核心概念

了解 Convai Unity SDK 在运行时如何工作——连接、会话、具身化、对话状态以及事件驱动响应。

“核心概念”一节介绍了场景中每个 Convai 角色背后运行的系统：管理连接的运行时层、控制每个角色生命周期的会话状态机、驱动 Gaze 和 Emotion 等模块的角色级具身层、控制发言者及发言时机的轮流发言系统，以及让场景能够响应运行时事件的事件组件。

如果你刚开始了解 SDK 内部机制，请从 **运行时架构** 开始。需要配置特定系统或了解 SDK 为何会以某种方式运行时，再阅读其他页面。

<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>运行时架构</strong><br>运行时层、接口清单，以及可替换的部分。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/runtime-architecture.md">运行时架构</a></td></tr><tr><td><strong>会话生命周期</strong><br>状态机、角色级会话、持久化和重新连接。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/session-lifecycle.md">会话生命周期</a></td></tr><tr><td><strong>角色具身</strong><br>角色级组合根、确定性更新，以及 Animator 和面部 blendshape 的单一写入者规则。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/character-embodiment.md">角色具身化</a></td></tr><tr><td><strong>对话状态</strong><br>每个具身模块都会读取的八值对话状态模型。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/dialogue-state.md">对话状态</a></td></tr><tr><td><strong>资源所有权与写时复制</strong><br>为什么编辑随包提供的配置文件会在项目中创建副本，而不是直接修改原文件。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/asset-ownership.md">资产所有权与写时复制</a></td></tr><tr><td><strong>轮流发言模式</strong><br>免提与按键通话——详解每个字段和策略。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/turn-taking-modes.md">轮流发言模式</a></td></tr><tr><td><strong>语音活动检测</strong><br>连接时确定采用服务器默认值还是自定义检测阈值。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/voice-activity-detection.md">语音活动检测</a></td></tr><tr><td><strong>事件系统</strong><br>中继组件、负载类型和订阅模式。</td><td><a href="https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts/event-system.md">事件系统</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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/convai-unity-sdk/core-concepts.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
